[release] Bye 2025 (#9702)

Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>

.github/copilot-instructions.md

@@ -0,0 +1,180 @@
+# GitHub Copilot Instructions for LLaMA Factory
+
+## Project Overview
+
+LLaMA Factory is an efficient fine-tuning framework for 100+ large language models (LLMs). It provides:
+- Support for various models: LLaMA, LLaVA, Mistral, Qwen, DeepSeek, Yi, Gemma, ChatGLM, Phi, etc.
+- Multiple training methods: pre-training, supervised fine-tuning, reward modeling, PPO, DPO, KTO, ORPO
+- Scalable resources: 16-bit full-tuning, freeze-tuning, LoRA and QLoRA variants
+- Advanced algorithms: GaLore, BAdam, APOLLO, Adam-mini, Muon, OFT, DoRA, etc.
+- Web UI (LLaMA Board) and CLI interfaces
+
+### Architecture Versions
+
+LLaMA Factory has two parallel architectures that can be switched via the `USE_V1` environment variable:
+
+**v0 (default)** - File hierarchy:
+- `api`, `webui` → `chat`, `eval`, `train` → `data`, `model` → `hparams` → `extras`
+
+**v1** - File hierarchy:
+- `trainers` → `core` → `accelerator`, `plugins`, `config` → `utils`
+
+Set `USE_V1=1` to enable v1 architecture.
+
+## Code Structure
+
+### v0 Architecture (Default)
+
+- `src/llamafactory/` - Main package directory
+  - `api/` - OpenAI-style API implementation
+  - `chat/` - Chat interface implementation
+  - `cli.py` - Command-line interface
+  - `data/` - Data processing and dataset handling
+  - `eval/` - Model evaluation utilities
+  - `extras/` - Additional utilities and helpers
+  - `hparams/` - Hyperparameter definitions
+  - `model/` - Model loading, patching, and utilities
+  - `train/` - Training pipeline implementation
+  - `webui/` - Gradio-based web interface
+- `src/train.py` - Training entry script (delegates to `llamafactory.train.tuner`)
+- `src/webui.py` - Web UI entry script (delegates to `llamafactory.webui.interface`)
+- `src/api.py` - API server entry script (delegates to `llamafactory.api.app`)
+- `tests/` - Test suite
+- `examples/` - Example configurations for various training scenarios
+- `data/` - Dataset definitions and examples
+
+### v1 Architecture (USE_V1=1)
+
+- `src/llamafactory/v1/` - Version 1 package directory
+  - `trainers/` - Training implementations
+  - `core/` - Core training utilities
+  - `accelerator/` - Acceleration and distributed training
+  - `plugins/` - Pluggable components (model, data, sampler, trainer)
+  - `config/` - Configuration management
+  - `utils/` - Utility functions
+
+## Development Practices
+
+### Code Style
+
+- Follow the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html)
+- Use ruff for linting and formatting
+- Line length: 119 characters
+- Indentation: 4 spaces
+- Quote style: double quotes
+- Use Google-style docstrings for documentation
+
+### Import Organization
+
+- Known first-party: `llamafactory`
+- Known third-party: `accelerate`, `datasets`, `gradio`, `numpy`, `peft`, `torch`, `transformers`, `trl`
+- Use 2 blank lines after imports
+
+### Quality Checks
+
+Before committing code, run:
+```bash
+make style      # Auto-fix style issues
+make quality    # Check code quality
+make test       # Run test suite
+```
+
+Or use the combined command:
+```bash
+make commit     # Run pre-commit hooks
+```
+
+### Testing
+
+- Use pytest for testing
+- Tests are located in `tests/` and `tests_v1/` directories
+- Run tests with: `make test` (which runs `WANDB_DISABLED=true pytest -vv --import-mode=importlib tests/ tests_v1/`)
+- Disable wandb during testing to avoid external dependencies
+- **Note**: Training configurations require GPU machines, so training is typically not tested end-to-end. Use `make test` to validate file-level functionality.
+
+### Building
+
+Build the package with:
+```bash
+pip3 install build && python3 -m build
+```
+
+### License
+
+- All source files must include the Apache 2.0 license header
+- Check license headers with: `make license`
+
+## Common Patterns
+
+### Configuration Files
+
+- Training configurations are typically YAML or JSON files in `examples/` directory
+- Hyperparameters are defined using dataclasses in `src/llamafactory/hparams/`
+
+### Model Support
+
+- New model support is added through model patches in `src/llamafactory/model/`
+- Visual models use the visual utilities in `src/llamafactory/model/model_utils/visual.py`
+- Quantization support is in `src/llamafactory/model/model_utils/quantization.py`
+
+### Data Processing
+
+- Dataset definitions are in `data/dataset_info.json`
+- Data templates and processors are in `src/llamafactory/data/`
+
+### Training
+
+- Training pipelines are in `src/llamafactory/train/`
+- Support for different training methods: SFT, DPO, PPO, RM, PT, KTO, ORPO
+
+## Key Dependencies
+
+- Python >= 3.9.0
+- PyTorch and transformers for model handling
+- datasets for data processing
+- peft for parameter-efficient fine-tuning
+- accelerate for distributed training
+- gradio for web UI
+- trl for reinforcement learning
+- Optional: vllm/sglang for inference, flash-attention-2, unsloth, liger-kernel
+
+## Entry Points
+
+- **CLI Training**: `llamafactory-cli train --config examples/train_lora/llama3_lora_sft.yaml`
+- **Web UI**: `llamafactory-cli webui` or `python src/webui.py`
+- **API Server**: `llamafactory-cli api` or `python src/api.py`
+- **Chat Interface**: `llamafactory-cli chat --model_name_or_path MODEL_PATH`
+
+## Environment Setup
+
+For development:
+```bash
+pip install -e ".[dev]"
+```
+
+## Important Notes
+
+- The project supports multiple backends: default PyTorch, vLLM, SGLang
+- Megatron-core training is supported via mcore_adapter
+- SwanLab and W&B are supported for experiment tracking
+- Docker support is available with pre-built images
+- Day-0/Day-1 support for latest cutting-edge models
+- Multi-modal support for vision and audio understanding tasks
+
+## Contribution Guidelines
+
+1. Fork the repository
+2. Create a development branch
+3. Set up development environment with `pip install -e ".[dev]"`
+4. Make changes following the style guide
+5. Run quality checks: `make style && make quality`
+6. Run tests: `make test`
+7. Submit a pull request
+
+## Common Commands
+
+- `make style` - Format code
+- `make quality` - Run linters
+- `make test` - Run tests
+- `make commit` - Install and run pre-commit hooks
+- `make license` - Check license headers

.github/workflows/docker.yml

@@ -7,7 +7,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "docker/**"
       - ".github/workflows/*.yml"
   pull_request:
@@ -15,7 +15,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "docker/**"
       - ".github/workflows/*.yml"
   release:
@@ -29,16 +29,13 @@ jobs:
       matrix:
         include:
           - device: "cuda"
-            npu_type: ""
+          - device: "npu-a2"
-          - device: "npu"
+          - device: "npu-a3"
-            npu_type: "a2"
-          - device: "npu"
-            npu_type: "a3"
 
     runs-on: ubuntu-latest
 
     concurrency:
-      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.device }}-${{ matrix.npu_type }}
+      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.device }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 
     environment:
@@ -55,16 +52,11 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-
       - name: Get llamafactory version
         id: version
         run: |
           if [ "${{ github.event_name }}" = "release" ]; then
-            echo "tag=$(python setup.py --version)" >> "$GITHUB_OUTPUT"
+            echo "tag=$(grep -oP 'VERSION = "\K[^"]+' src/llamafactory/extras/env.py)" >> "$GITHUB_OUTPUT"
           else
             echo "tag=latest" >> "$GITHUB_OUTPUT"
           fi
@@ -80,7 +72,7 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Login to Quay
-        if: ${{ github.event_name != 'pull_request' && matrix.device == 'npu'}}
+        if: ${{ github.event_name != 'pull_request' && startsWith(matrix.device, 'npu') }}
         uses: docker/login-action@v3
         with:
           registry: quay.io
@@ -93,16 +85,12 @@ jobs:
         with:
           context: .
           file: ./docker/docker-cuda/Dockerfile
-          build-args: |
-            EXTRAS=metrics,deepspeed,liger-kernel
           push: ${{ github.event_name != 'pull_request' }}
           tags: |
             docker.io/hiyouga/llamafactory:${{ steps.version.outputs.tag }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
 
       - name: Build and push Docker image (NPU-A2)
-        if: ${{ matrix.device == 'npu' && matrix.npu_type == 'a2' }}
+        if: ${{ matrix.device == 'npu-a2' }}
         uses: docker/build-push-action@v6
         with:
           context: .
@@ -112,11 +100,9 @@ jobs:
           tags: |
             docker.io/hiyouga/llamafactory:${{ steps.version.outputs.tag }}-npu-a2
             quay.io/ascend/llamafactory:${{ steps.version.outputs.tag }}-npu-a2
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
 
       - name: Build and push Docker image (NPU-A3)
-        if: ${{ matrix.device == 'npu' && matrix.npu_type == 'a3' }}
+        if: ${{ matrix.device == 'npu-a3' }}
         uses: docker/build-push-action@v6
         with:
           context: .
@@ -128,5 +114,3 @@ jobs:
           tags: |
             docker.io/hiyouga/llamafactory:${{ steps.version.outputs.tag }}-npu-a3
             quay.io/ascend/llamafactory:${{ steps.version.outputs.tag }}-npu-a3
-          cache-from: type=gha
-          cache-to: type=gha,mode=max

.github/workflows/publish.yml

@@ -23,10 +23,11 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python
+      - name: Install uv
-        uses: actions/setup-python@v5
+        uses: astral-sh/setup-uv@v7
         with:
-          python-version: "3.9"
+          python-version: "3.11"
+          github-token: ${{ github.token }}
 
       - name: Build package
         run: |

.github/workflows/tests.yml

@@ -7,7 +7,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "Makefile"
       - ".github/workflows/*.yml"
   pull_request:
@@ -15,7 +15,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "Makefile"
       - ".github/workflows/*.yml"
 
@@ -25,29 +25,25 @@ jobs:
       fail-fast: false
       matrix:
         python:
-          - "3.9"
-          - "3.10"
           - "3.11"
           - "3.12"
+          - "3.13"
         os:
           - "ubuntu-latest"
           - "windows-latest"
           - "macos-latest"
         transformers:
-          - null
+          - ""
         include:  # test backward compatibility
-          - python: "3.9"
+          - python: "3.11"
-            os: "ubuntu-latest"
-            transformers: "4.49.0"
-          - python: "3.9"
             os: "ubuntu-latest"
             transformers: "4.51.0"
-          - python: "3.9"
+          - python: "3.11"
             os: "ubuntu-latest"
             transformers: "4.53.0"
-        exclude:  # exclude python 3.9 on macos
+          - python: "3.11"
-          - python: "3.9"
+            os: "ubuntu-latest"
-            os: "macos-latest"
+            transformers: "4.55.0"
 
     runs-on: ${{ matrix.os }}
 
@@ -63,22 +59,23 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python
+      - name: Install uv
-        uses: actions/setup-python@v5
+        uses: astral-sh/setup-uv@v7
         with:
           python-version: ${{ matrix.python }}
-          cache: "pip"
+          github-token: ${{ github.token }}
-          cache-dependency-path: "**/requirements*.txt"
+          enable-cache: false
 
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
+          uv venv
-          python -m pip install ".[torch,dev]"
+          uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+          uv pip install -e ".[dev]"
 
       - name: Install transformers
         if: ${{ matrix.transformers }}
         run: |
-          python -m pip install "transformers==${{ matrix.transformers }}"
+          uv pip install "transformers==${{ matrix.transformers }}"
 
       - name: Cache files
         id: hf-hub-cache
@@ -90,18 +87,25 @@ jobs:
       - name: Check quality
         run: |
           make style && make quality
+        env:
+          UV_NO_SYNC: 1
 
       - name: Check license
         run: |
           make license
+        env:
+          UV_NO_SYNC: 1
 
       - name: Check build
         run: |
           make build
+        env:
+          UV_NO_SYNC: 1
 
       - name: Test with pytest
         run: |
           make test
         env:
+          UV_NO_SYNC: 1
           HF_HOME: ${{ runner.temp }}/huggingface
           HF_HUB_OFFLINE: "${{ steps.hf-hub-cache.outputs.cache-hit == 'true' && '1' || '0' }}"

.github/workflows/tests_cuda.yml

@@ -0,0 +1,88 @@
+name: tests_cuda
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - "main"
+    paths:
+      - "**/*.py"
+      - "pyproject.toml"
+      - "Makefile"
+      - ".github/workflows/*.yml"
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - "**/*.py"
+      - "pyproject.toml"
+      - "Makefile"
+      - ".github/workflows/*.yml"
+
+jobs:
+  tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        python:
+          - "3.11"
+        os:
+          - "linux-x86_64-gpu-2"
+
+    runs-on: ${{ matrix.os }}
+
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.os }}-${{ matrix.python }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ matrix.python }}
+          github-token: ${{ github.token }}
+          enable-cache: false
+
+      - name: Check GPU Status
+        run: nvidia-smi
+
+      - name: Install dependencies
+        run: |
+          uv venv
+          uv pip install -e ".[dev]"
+
+      - name: Cache HuggingFace models
+        id: hf-hub-cache
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.temp }}/huggingface
+          key: hf-cache-${{ runner.os }}-${{ hashFiles('tests/version.txt') }}
+
+      - name: Check quality
+        run: |
+          make style && make quality
+        env:
+          UV_NO_SYNC: 1
+
+      - name: Check license
+        run: |
+          make license
+        env:
+          UV_NO_SYNC: 1
+
+      - name: Check build
+        run: |
+          make build
+        env:
+          UV_NO_SYNC: 1
+
+      - name: Test with pytest
+        run: |
+          make test
+        env:
+          UV_NO_SYNC: 1
+          HF_HOME: ${{ runner.temp }}/huggingface
+          HF_HUB_OFFLINE: "${{ steps.hf-hub-cache.outputs.cache-hit == 'true' && '1' || '0' }}"

.github/workflows/tests_npu.yml

@@ -7,7 +7,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "Makefile"
       - ".github/workflows/*.yml"
   pull_request:
@@ -15,7 +15,7 @@ on:
       - "main"
     paths:
       - "**/*.py"
-      - "requirements.txt"
+      - "pyproject.toml"
       - "Makefile"
       - ".github/workflows/*.yml"
 
@@ -48,10 +48,18 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ matrix.python }}
+          github-token: ${{ github.token }}
+          enable-cache: false
+
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
+          uv venv
-          python -m pip install ".[torch-npu,dev]" torch-npu==${{matrix.pytorch_npu}}
+          uv pip install torch-npu==${{matrix.pytorch_npu}}
+          uv pip install -e ".[dev]"
 
       - name: Install node
         run: |
@@ -70,18 +78,25 @@ jobs:
       - name: Check quality
         run: |
           make style && make quality
+        env:
+          UV_NO_SYNC: 1
 
       - name: Check license
         run: |
           make license
+        env:
+          UV_NO_SYNC: 1
 
       - name: Check build
         run: |
           make build
+        env:
+          UV_NO_SYNC: 1
 
       - name: Test with pytest
         run: |
           make test
         env:
+          UV_NO_SYNC: 1
           HF_HOME: /root/.cache/huggingface
           HF_HUB_OFFLINE: "${{ steps.hf-hub-cache.outputs.cache-hit == 'true' && '1' || '0' }}"

.gitignore

@@ -85,7 +85,7 @@ 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
+.python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.

MANIFEST.in

@@ -1 +1 @@
-include LICENSE requirements.txt
+include LICENSE

Makefile

@@ -1,24 +1,28 @@
 .PHONY: build commit license quality style test
 
-check_dirs := scripts src tests tests_v1 setup.py
+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:
-	pip3 install build && python3 -m build
+	$(BUILD)
 
 commit:
-	pre-commit install
+	$(TOOL) pre-commit install
-	pre-commit run --all-files
+	$(TOOL) pre-commit run --all-files
 
 license:
-	python3 tests/check_license.py $(check_dirs)
+	$(RUN) python3 tests/check_license.py $(check_dirs)
 
 quality:
-	ruff check $(check_dirs)
+	$(TOOL) ruff check $(check_dirs)
-	ruff format --check $(check_dirs)
+	$(TOOL) ruff format --check $(check_dirs)
 
 style:
-	ruff check $(check_dirs) --fix
+	$(TOOL) ruff check $(check_dirs) --fix
-	ruff format $(check_dirs)
+	$(TOOL) ruff format $(check_dirs)
 
 test:
-	CUDA_VISIBLE_DEVICES= ASCEND_RT_VISIBLE_DEVICES=0 WANDB_DISABLED=true pytest -vv --import-mode=importlib tests/ tests_v1/
+	WANDB_DISABLED=true $(RUN) pytest -vv --import-mode=importlib tests/ tests_v1/

README.md

@@ -278,27 +278,21 @@ Read technical notes:
 
 | Model                                                             | Model size                       | Template             |
 | ----------------------------------------------------------------- | -------------------------------- | -------------------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2            |
 | [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                    |
-| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3             |
 | [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere               |
-| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek             |
+| [DeepSeek (LLM/Code/MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek             |
-| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3            |
+| [DeepSeek 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/ernie_nothink  |
-| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon               |
+| [Falcon/Falcon H1](https://huggingface.co/tiiuae)                 | 0.5B/1.5B/3B/7B/11B/34B/40B/180B | falcon/falcon_h1     |
-| [Falcon-H1](https://huggingface.co/tiiuae)                        | 0.5B/1.5B/3B/7B/34B              | 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-4.1V](https://huggingface.co/zai-org)                        | 9B                               | glm4v                |
 | [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                  |
+| [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt_oss              |
-| [Granite 3.0-3.3](https://huggingface.co/ibm-granite)             | 1B/2B/3B/8B                      | granite3             |
+| [Granite 3-4](https://huggingface.co/ibm-granite)                 | 1B/2B/3B/7B/8B                   | granite3/granite4    |
-| [Granite 4](https://huggingface.co/ibm-granite)                   | 7B                               | granite4             |
 | [Hunyuan (MT)](https://huggingface.co/tencent/)                   | 7B                               | hunyuan              |
-| [Index](https://huggingface.co/IndexTeam)                         | 1.9B                             | index                |
 | [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            |
 | [InternLM/Intern-S1-mini](https://huggingface.co/internlm/)       | 8B                               | intern_s1            |
@@ -312,15 +306,14 @@ Read technical notes:
 | [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                               | mimo                 |
+| [MiMo](https://huggingface.co/XiaomiMiMo)                         | 7B/309B                          | mimo/mimo_v2         |
 | [MiniCPM 1-4.1](https://huggingface.co/openbmb)                   | 0.5B/1B/2B/4B/8B                 | cpm/cpm3/cpm4        |
 | [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v  |
-| [Ministral(3)/Mistral-Nemo](https://huggingface.co/mistralai)     | 3B/8B/12B/14B                    | ministral/ministral3 |
+| [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              |
-| [Mistral Small](https://huggingface.co/mistralai)                 | 24B                              | mistral_small        |
 | [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                    |
 | [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma            |
-| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                    |
 | [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                  |
 | [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small            |
 | [Phi-4](https://huggingface.co/microsoft)                         | 14B                              | phi4                 |
@@ -333,12 +326,9 @@ Read technical notes:
 | [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  |
-| [Skywork o1](https://huggingface.co/Skywork)                      | 8B                               | skywork_o1           |
 | [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                    |
-| [TeleChat2](https://huggingface.co/Tele-AI)                       | 3B/7B/35B/115B                   | telechat2            |
+| [VibeThinker-1.5B](https://huggingface.co/WeiboAI)                | 1.5B                             | qwen3                |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse               |
 | [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi                   |
-| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl                |
 | [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan                 |
 
 > [!NOTE]
@@ -444,6 +434,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [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)
@@ -525,10 +516,12 @@ huggingface-cli login
 ```bash
 git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e ".[torch,metrics]" --no-build-isolation
+pip install -e ".[metrics]"
 ```
 
-Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, aqlm, vllm, sglang, galore, apollo, badam, adam-mini, qwen, minicpm_v, openmind, swanlab, dev
+Optional dependencies available: `metrics`, `deepspeed`. Install with: `pip install -e ".[metrics,deepspeed]"`
+
+Additional dependencies for specific features are available in `examples/requirements/`.
 
 #### Install from Docker Image
 
@@ -547,13 +540,7 @@ Please refer to [build docker](#build-docker) to build the image yourself.
 Create an isolated Python environment with [uv](https://github.com/astral-sh/uv):
 
 ```bash
-uv sync --extra torch --extra metrics --prerelease=allow
+uv run llamafactory-cli webui
-```
-
-Run LLaMA-Factory in the isolated environment:
-
-```bash
-uv run --prerelease=allow llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
 ```
 
 </details>
@@ -590,7 +577,7 @@ To enable FlashAttention-2 on the Windows platform, please use the script from [
 
 <details><summary>For Ascend NPU users</summary>
 
-To install LLaMA Factory on Ascend NPU devices, please upgrade Python to version 3.10 or higher and specify extra dependencies: `pip install -e ".[torch-npu,metrics]"`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:
+To install LLaMA Factory on Ascend NPU devices, please upgrade Python to version 3.10 or higher: `pip install -e . torch-npu==2.7.1`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:
 
 ```bash
 # replace the url according to your CANN version and devices
@@ -609,8 +596,8 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | Requirement  | Minimum | Recommend      |
 | ------------ | ------- | -------------- |
 | CANN         | 8.0.RC1 | 8.0.0.alpha002 |
-| torch        | 2.1.0   | 2.4.0          |
+| torch        | 2.1.0   | 2.7.1          |
-| torch-npu    | 2.1.0   | 2.4.0.post2    |
+| torch-npu    | 2.1.0   | 2.7.1          |
 | deepspeed    | 0.13.2  | 0.13.2         |
 | vllm-ascend  | -       | 0.7.3          |
 
@@ -652,7 +639,7 @@ cd transformers
 pip install .
 ```
 
-3. Set `double_quantization: false` in the configuration. You can refer to the [example](examples/train_qlora/llama3_lora_sft_bnb_npu.yaml).
+3. Set `double_quantization: false` in the configuration. You can refer to the [example](examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml).
 
 </details>
 
@@ -667,12 +654,12 @@ You can also use **[Easy Dataset](https://github.com/ConardLi/easy-dataset)**, *
 
 ### Quickstart
 
-Use the following 3 commands to run LoRA **fine-tuning**, **inference** and **merging** of the Llama3-8B-Instruct model, respectively.
+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/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
-llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
-llamafactory-cli export examples/merge_lora/llama3_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).
@@ -725,7 +712,6 @@ For CUDA users:
 ```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 \
@@ -742,7 +728,6 @@ For Ascend NPU users:
 ```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 \
@@ -767,7 +752,6 @@ For AMD ROCm users:
 ```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 \
@@ -798,7 +782,7 @@ When building the Docker image, use `-v ./hf_cache:/root/.cache/huggingface` arg
 ### Deploy with OpenAI-style API and vLLM
 
 ```bash
-API_PORT=8000 llamafactory-cli api examples/inference/llama3.yaml infer_backend=vllm vllm_enforce_eager=true
+API_PORT=8000 llamafactory-cli api examples/inference/qwen3.yaml infer_backend=vllm vllm_enforce_eager=true
 ```
 
 > [!TIP]

README_zh.md

@@ -280,27 +280,21 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 
 | 模型名                                                             | 参数量                            | Template             |
 | ----------------------------------------------------------------- | -------------------------------- | -------------------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2            |
 | [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                    |
-| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3             |
 | [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere               |
-| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek             |
+| [DeepSeek (LLM/Code/MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek             |
-| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3            |
+| [DeepSeek 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/ernie_nothink  |
-| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon               |
+| [Falcon/Falcon H1](https://huggingface.co/tiiuae)                 | 0.5B/1.5B/3B/7B/11B/34B/40B/180B | falcon/falcon_h1     |
-| [Falcon-H1](https://huggingface.co/tiiuae)                        | 0.5B/1.5B/3B/7B/34B              | 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-4.1V](https://huggingface.co/zai-org)                        | 9B                               | glm4v                |
 | [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                  |
+| [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt_oss              |
-| [Granite 3.0-3.3](https://huggingface.co/ibm-granite)             | 1B/2B/3B/8B                      | granite3             |
+| [Granite 3-4](https://huggingface.co/ibm-granite)                 | 1B/2B/3B/7B/8B                   | granite3/granite4    |
-| [Granite 4](https://huggingface.co/ibm-granite)                   | 7B                               | granite4             |
 | [Hunyuan (MT)](https://huggingface.co/tencent/)                   | 7B                               | hunyuan              |
-| [Index](https://huggingface.co/IndexTeam)                         | 1.9B                             | index                |
 | [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            |
 | [InternLM/Intern-S1-mini](https://huggingface.co/internlm/)       | 8B                               | intern_s1            |
@@ -314,15 +308,14 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 | [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                               | mimo                 |
+| [MiMo](https://huggingface.co/XiaomiMiMo)                         | 7B/309B                          | mimo/mimo_v2         |
 | [MiniCPM 1-4.1](https://huggingface.co/openbmb)                   | 0.5B/1B/2B/4B/8B                 | cpm/cpm3/cpm4        |
 | [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v  |
-| [Ministral(3)/Mistral-Nemo](https://huggingface.co/mistralai)     | 3B/8B/12B/14B                    | ministral/ministral3 |
+| [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              |
-| [Mistral Small](https://huggingface.co/mistralai)                 | 24B                              | mistral_small        |
 | [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                    |
 | [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma            |
-| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                    |
 | [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                  |
 | [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small            |
 | [Phi-4](https://huggingface.co/microsoft)                         | 14B                              | phi4                 |
@@ -335,12 +328,9 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 | [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  |
-| [Skywork o1](https://huggingface.co/Skywork)                      | 8B                               | skywork_o1           |
 | [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                    |
-| [TeleChat2](https://huggingface.co/Tele-AI)                       | 3B/7B/35B/115B                   | telechat2            |
+| [VibeThinker-1.5B](https://huggingface.co/WeiboAI)                | 1.5B                             | qwen3                |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse               |
 | [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi                   |
-| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl                |
 | [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan                 |
 
 > [!NOTE]
@@ -446,6 +436,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 - [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)
@@ -527,10 +518,12 @@ huggingface-cli login
 ```bash
 git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e ".[torch,metrics]" --no-build-isolation
+pip install -e ".[metrics]"
 ```
 
-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、aqlm、vllm、sglang、galore、apollo、badam、adam-mini、qwen、minicpm_v、openmind、swanlab、dev
+可选的额外依赖项：`metrics`、`deepspeed`。使用 `pip install -e ".[metrics,deepspeed]"` 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
 
@@ -549,13 +542,7 @@ docker run -it --rm --gpus=all --ipc=host hiyouga/llamafactory:latest
 使用 [uv](https://github.com/astral-sh/uv) 创建隔离的 Python 环境：
 
 ```bash
-uv sync --extra torch --extra metrics --prerelease=allow
+uv run llamafactory-cli webui
-```
-
-在环境中运行 LLaMA-Factory：
-
-```bash
-uv run --prerelease=allow llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
 ```
 
 </details>
@@ -592,7 +579,7 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl
 
 <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 -e ".[torch-npu,metrics]"` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit 与 Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
+在昇腾 NPU 设备上安装 LLaMA Factory 时，请升级 Python 到 3.10 及以上，并需要指定额外依赖项，使用 `pip install -e . torch-npu==2.7.1` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit 与 Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
 
 ```bash
 # 请替换 URL 为 CANN 版本和设备型号对应的 URL
@@ -611,8 +598,8 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | 依赖项        | 至少     | 推荐           |
 | ------------ | ------- | -------------- |
 | CANN         | 8.0.RC1 | 8.0.0.alpha002 |
-| torch        | 2.1.0   | 2.4.0          |
+| torch        | 2.1.0   | 2.7.1          |
-| torch-npu    | 2.1.0   | 2.4.0.post2    |
+| torch-npu    | 2.1.0   | 2.7.1          |
 | deepspeed    | 0.13.2  | 0.13.2         |
 | vllm-ascend  | -       | 0.7.3          |
 
@@ -654,7 +641,7 @@ cd transformers
 pip install .
 ```
 
-3. 在训练参数中设置 `double_quantization: false`，可参考[示例](examples/train_qlora/llama3_lora_sft_bnb_npu.yaml)。
+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>
 
@@ -669,12 +656,12 @@ pip install .
 
 ### 快速开始
 
-下面三行命令分别对 Llama3-8B-Instruct 模型进行 LoRA **微调**、**推理**和**合并**。
+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/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
-llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
-llamafactory-cli export examples/merge_lora/llama3_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）。
@@ -800,7 +787,7 @@ docker exec -it llamafactory bash
 ### 利用 vLLM 部署 OpenAI API
 
 ```bash
-API_PORT=8000 llamafactory-cli api examples/inference/llama3.yaml infer_backend=vllm vllm_enforce_eager=true
+API_PORT=8000 llamafactory-cli api examples/inference/qwen3.yaml infer_backend=vllm vllm_enforce_eager=true
 ```
 
 > [!TIP]

data/dataset_info.json

@@ -471,6 +471,14 @@
   "ultrachat_de": {
     "hf_hub_url": "mayflowergmbh/ultra-chat_de"
   },
+  "dlr_web": {
+    "hf_hub_url": "Attention1115/DLR-Web",
+    "split": "full",
+    "columns": {
+      "prompt": "question",
+      "response": "response"
+    }
+  },
   "dpo_en_demo": {
     "file_name": "dpo_en_demo.json",
     "ranking": true,

docker/docker-cuda/Dockerfile

@@ -4,7 +4,6 @@ FROM ${BASE_IMAGE}
 
 # Installation arguments
 ARG PIP_INDEX=https://pypi.org/simple
-ARG EXTRAS=metrics
 ARG INSTALL_FLASHATTN=false
 ARG HTTP_PROXY=""
 
@@ -27,17 +26,13 @@ WORKDIR /app
 # Change pip source
 RUN pip config set global.index-url "${PIP_INDEX}" && \
     pip config set global.extra-index-url "${PIP_INDEX}" && \
-    pip install --no-cache-dir --upgrade pip packaging wheel setuptools
+    pip install --no-cache-dir --upgrade pip packaging wheel setuptools editables "hatchling>=1.18.0"
 
-# Install the requirements
+# Copy the application into the image
-COPY requirements.txt /app
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the application into the image
 COPY . /app
 
 # Install LLaMA Factory
-RUN pip install --no-cache-dir -e ".[${EXTRAS}]" --no-build-isolation
+RUN pip install --no-cache-dir --no-build-isolation -e ".[metrics,deepspeed]"
 
 # Rebuild flash attention
 RUN if [ "${INSTALL_FLASHATTN}" == "true" ]; then \

docker/docker-cuda/Dockerfile.megatron

@@ -8,7 +8,7 @@ ENV PYPI_MIRROR=https://mirrors.aliyun.com/pypi/simple/
 ENV PYPI_TRUSTED_HOST=mirrors.aliyun.com
 ENV APT_MIRROR=https://mirrors.tuna.tsinghua.edu.cn/ubuntu/
 
-RUN pip install --upgrade pip setuptools wheel --trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
+RUN pip install --upgrade pip setuptools wheel "hatchling>=1.18.0" editables --trusted-host ${PYPI_TRUSTED_HOST} --index-url ${PYPI_MIRROR}
 
 RUN pip uninstall -y torch torchvision torch-tensorrt \
     flash_attn transformer-engine \
@@ -56,14 +56,14 @@ ENV JAVA_HOME /usr/lib/jvm/java-21-openjdk-amd64
 # pip install LLaMA-Factory
 WORKDIR /app
 
-COPY requirements.txt /app/
+# Copy the application into the image
-RUN pip install --no-cache-dir -r requirements.txt
+COPY . /app
+
+# Install LLaMA Factory
+RUN pip install --no-cache-dir -e ".[metrics]" --no-build-isolation
 
 RUN pip install "git+https://github.com/alibaba/roll.git#subdirectory=mcore_adapter"
 
-COPY . /app/
-RUN pip install -e ".[metrics]" --no-build-isolation
-
 # Expose port 7860 for LLaMA Board
 ENV GRADIO_SERVER_PORT=7860
 EXPOSE 7860

docker/docker-cuda/docker-compose.yml

@@ -5,7 +5,6 @@ services:
       context: ../..
       args:
         PIP_INDEX: https://pypi.org/simple
-        EXTRAS: metrics
     container_name: llamafactory
     ports:
       - "7860:7860"

docker/docker-npu/Dockerfile

@@ -5,7 +5,6 @@ FROM ${BASE_IMAGE}
 
 # Installation arguments
 ARG PIP_INDEX=https://pypi.org/simple
-ARG EXTRAS=torch-npu,metrics
 ARG HTTP_PROXY=""
 ARG PYTORCH_INDEX=https://download.pytorch.org/whl/cpu
 
@@ -28,21 +27,15 @@ WORKDIR /app
 # Change pip source
 RUN pip config set global.index-url "${PIP_INDEX}" && \
     pip config set global.extra-index-url "${PIP_INDEX}" && \
-    pip install --no-cache-dir --upgrade pip packaging wheel setuptools
+    pip install --no-cache-dir --upgrade pip packaging wheel setuptools editables "hatchling>=1.18.0"
+
+# Copy the application into the image
+COPY . /app
 
 # Install torch-npu
 RUN pip uninstall -y torch torchvision torchaudio && \
-    pip install --no-cache-dir "torch==2.7.1" "torch-npu==2.7.1" "torchvision==0.22.1" --index-url "${PYTORCH_INDEX}"
+    pip install --no-cache-dir "torch==2.7.1" "torch-npu==2.7.1" "torchvision==0.22.1" "torchaudio==2.7.1" --index-url "${PYTORCH_INDEX}" && \
-
+    pip install --no-cache-dir -e ".[metrics]" --no-build-isolation
-# Install the requirements
-COPY requirements.txt /app
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the application into the image
-COPY . /app
-
-# Install LLaMA Factory
-RUN pip install --no-cache-dir -e ".[${EXTRAS}]" --no-build-isolation
 
 # Set up volumes
 # VOLUME [ "/root/.cache/huggingface", "/app/shared_data", "/app/output" ]

docker/docker-npu/docker-compose.yml

@@ -5,7 +5,6 @@ services:
       context: ../..
       args:
         PIP_INDEX: https://pypi.org/simple
-        EXTRAS: torch-npu,metrics
     container_name: llamafactory-a2
     image: llamafactory:npu-a2
     volumes:
@@ -36,7 +35,6 @@ services:
       args:
         BASE_IMAGE: quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
         PIP_INDEX: https://pypi.org/simple
-        EXTRAS: torch-npu,metrics
     container_name: llamafactory-a3
     image: llamafactory:npu-a3
     volumes:

docker/docker-rocm/Dockerfile

@@ -4,7 +4,6 @@ FROM ${BASE_IMAGE}
 
 # Installation arguments
 ARG PIP_INDEX=https://pypi.org/simple
-ARG EXTRAS=metrics
 ARG INSTALL_FLASHATTN=false
 ARG HTTP_PROXY=""
 ARG PYTORCH_INDEX=https://download.pytorch.org/whl/rocm6.3
@@ -28,21 +27,14 @@ WORKDIR /app
 # Change pip source
 RUN pip config set global.index-url "${PIP_INDEX}" && \
     pip config set global.extra-index-url "${PIP_INDEX}" && \
-    pip install --no-cache-dir --upgrade pip packaging wheel setuptools
+    pip install --no-cache-dir --upgrade pip packaging wheel setuptools editables "hatchling>=1.18.0"
 
-# Reinstall pytorch rocm
+# Copy the application into the image
-RUN pip uninstall -y torch torchvision torchaudio && \
-    pip install --no-cache-dir --pre torch torchvision torchaudio --index-url "${PYTORCH_INDEX}"
-
-# Install the requirements
-COPY requirements.txt /app
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the application into the image
 COPY . /app
 
-# Install LLaMA Factory
+# Reinstall pytorch rocm and install LLaMA Factory
-RUN pip install --no-cache-dir -e ".[${EXTRAS}]" --no-build-isolation
+RUN pip uninstall -y torch torchvision torchaudio && \
+    pip install --no-cache-dir --no-build-isolation -e --pre ".[metrics,deepspeed]" --index-url "${PYTORCH_INDEX}"
 
 # Rebuild flash attention
 RUN if [ "${INSTALL_FLASHATTN}" == "true" ]; then \

docker/docker-rocm/docker-compose.yml

@@ -5,7 +5,6 @@ services:
       context: ../..
       args:
         PIP_INDEX: https://pypi.org/simple
-        EXTRAS: metrics
     container_name: llamafactory
     ports:
       - "7860:7860"

examples/README.md

@@ -18,19 +18,19 @@ By default, LLaMA-Factory uses all visible computing devices.
 Basic usage:
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 Advanced usage:
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml \
     learning_rate=1e-5 \
     logging_steps=1
 ```
 
 ```bash
-bash examples/train_lora/llama3_lora_sft.sh
+bash examples/train_lora/qwen3_lora_sft.sh
 ```
 
 ## Examples
@@ -40,49 +40,43 @@ bash examples/train_lora/llama3_lora_sft.sh
 #### (Continuous) Pre-Training
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_pretrain.yaml
 ```
 
 #### Supervised Fine-Tuning
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 #### Multimodal Supervised Fine-Tuning
 
 ```bash
-llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3vl_lora_sft.yaml
 ```
 
 #### DPO/ORPO/SimPO Training
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_dpo.yaml
 ```
 
 #### Multimodal DPO/ORPO/SimPO Training
 
 ```bash
-llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml
+llamafactory-cli train examples/train_lora/qwen3vl_lora_dpo.yaml
 ```
 
 #### Reward Modeling
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_reward.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_reward.yaml
-```
-
-#### PPO Training
-
-```bash
-llamafactory-cli train examples/train_lora/llama3_lora_ppo.yaml
 ```
 
 #### KTO Training
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_kto.yaml
 ```
 
 #### Preprocess Dataset
@@ -90,32 +84,26 @@ llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
 It is useful for large dataset, use `tokenized_path` in config to load the preprocessed dataset.
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_preprocess.yaml
+llamafactory-cli train examples/train_lora/qwen3_preprocess.yaml
-```
-
-#### Evaluating on MMLU/CMMLU/C-Eval Benchmarks
-
-```bash
-llamafactory-cli eval examples/train_lora/llama3_lora_eval.yaml
 ```
 
 #### Supervised Fine-Tuning on Multiple Nodes
 
 ```bash
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 #### Supervised Fine-Tuning with DeepSpeed ZeRO-3 (Weight Sharding)
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ds3.yaml
 ```
 
 #### Supervised Fine-Tuning with Ray on 4 GPUs
 
 ```bash
-USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
+USE_RAY=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ray.yaml
 ```
 
 ### QLoRA Fine-Tuning
@@ -123,13 +111,13 @@ USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
 #### Supervised Fine-Tuning with 4/8-bit Bitsandbytes/HQQ/EETQ Quantization (Recommended)
 
 ```bash
-llamafactory-cli train examples/train_qlora/llama3_lora_sft_otfq.yaml
+llamafactory-cli train examples/train_qlora/qwen3_lora_sft_otfq.yaml
 ```
 
 #### Supervised Fine-Tuning with 4-bit Bitsandbytes Quantization on Ascend NPU
 
 ```bash
-llamafactory-cli train examples/train_qlora/llama3_lora_sft_bnb_npu.yaml
+llamafactory-cli train examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml
 ```
 
 #### Supervised Fine-Tuning with 4/8-bit GPTQ Quantization
@@ -155,14 +143,14 @@ llamafactory-cli train examples/train_qlora/llama3_lora_sft_aqlm.yaml
 #### Supervised Fine-Tuning on Single Node
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 #### Supervised Fine-Tuning on Multiple Nodes
 
 ```bash
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 ### Elastic and Fault-Tolerant Supervised Fine-Tuning on Multiple Nodes
@@ -170,13 +158,13 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500
 To launch an elastic job with `MAX_RESTARTS` failures retries, run the following on at least `MIN_NNODES` nodes and at most `MAX_NNODES` nodes. `RDZV_ID` should be set as a unique job id (shared by all nodes participating in the job). See also [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html).
 
 ```bash
-FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 #### Multimodal Supervised Fine-Tuning
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3vl_full_sft.yaml
 ```
 
 ### Merging LoRA Adapters and Quantization
@@ -186,19 +174,19 @@ FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.y
 Note: DO NOT use quantized model or `quantization_bit` when merging LoRA adapters.
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
 ```
 
 #### Quantizing Model using AutoGPTQ
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
+llamafactory-cli export examples/merge_lora/qwen3_gptq.yaml
 ```
 
 ### Save Ollama modelfile
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_full_sft.yaml
 ```
 
 ### Inferring LoRA Fine-Tuned Models
@@ -206,26 +194,26 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
 #### Evaluation using vLLM's Multi-GPU Inference
 
 ```
-python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
+python scripts/vllm_infer.py --model_name_or_path Qwen/Qwen3-4B-Instruct-2507 --template qwen3_nothink --dataset alpaca_en_demo
 python scripts/eval_bleu_rouge.py generated_predictions.jsonl
 ```
 
 #### Use CLI ChatBox
 
 ```bash
-llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
 ```
 
 #### Use Web UI ChatBox
 
 ```bash
-llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli webchat examples/inference/qwen3_lora_sft.yaml
 ```
 
 #### Launch OpenAI-style API
 
 ```bash
-llamafactory-cli api examples/inference/llama3_lora_sft.yaml
+llamafactory-cli api examples/inference/qwen3_lora_sft.yaml
 ```
 
 ### Extras

examples/README_zh.md

@@ -18,19 +18,19 @@ LLaMA-Factory 默认使用所有可见的计算设备。
 基础用法：
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 高级用法：
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml \
     learning_rate=1e-5 \
     logging_steps=1
 ```
 
 ```bash
-bash examples/train_lora/llama3_lora_sft.sh
+bash examples/train_lora/qwen3_lora_sft.sh
 ```
 
 ## 示例
@@ -40,49 +40,43 @@ bash examples/train_lora/llama3_lora_sft.sh
 #### （增量）预训练
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_pretrain.yaml
 ```
 
 #### 指令监督微调
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 #### 多模态指令监督微调
 
 ```bash
-llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml
+llamafactory-cli train examples/train_lora/qwen3vl_lora_sft.yaml
 ```
 
 #### DPO/ORPO/SimPO 训练
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_dpo.yaml
 ```
 
 #### 多模态 DPO/ORPO/SimPO 训练
 
 ```bash
-llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml
+llamafactory-cli train examples/train_lora/qwen3vl_lora_dpo.yaml
 ```
 
 #### 奖励模型训练
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_reward.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_reward.yaml
-```
-
-#### PPO 训练
-
-```bash
-llamafactory-cli train examples/train_lora/llama3_lora_ppo.yaml
 ```
 
 #### KTO 训练
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
+llamafactory-cli train examples/train_lora/qwen3_lora_kto.yaml
 ```
 
 #### 预处理数据集
@@ -90,20 +84,14 @@ llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
 对于大数据集有帮助，在配置中使用 `tokenized_path` 以加载预处理后的数据集。
 
 ```bash
-llamafactory-cli train examples/train_lora/llama3_preprocess.yaml
+llamafactory-cli train examples/train_lora/qwen3_preprocess.yaml
-```
-
-#### 在 MMLU/CMMLU/C-Eval 上评估
-
-```bash
-llamafactory-cli eval examples/train_lora/llama3_lora_eval.yaml
 ```
 
 #### 多机指令监督微调
 
 ```bash
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
 ```
 
 ### 支持弹性和容错的多机指令监督微调
@@ -111,19 +99,19 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500
 要启动一个支持弹性节点和容错的多机指令微调，在每个节点上执行以下命令。弹性节点数量范围为 `MIN_NNODES:MAX_NNODES`，每个节点最多允许因为错误重启 `MAX_RESTARTS` 次。`RDZV_ID` 应设置为一个唯一的作业 ID（由参与该作业的所有节点共享）。更多新可以参考官方文档 [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html)。
 
 ```bash
-FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 #### 使用 DeepSpeed ZeRO-3 平均分配显存
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ds3.yaml
 ```
 
 #### 使用 Ray 在 4 张 GPU 上微调
 
 ```bash
-USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
+USE_RAY=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ray.yaml
 ```
 
 ### QLoRA 微调
@@ -131,13 +119,13 @@ USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
 #### 基于 4/8 比特 Bitsandbytes/HQQ/EETQ 量化进行指令监督微调（推荐）
 
 ```bash
-llamafactory-cli train examples/train_qlora/llama3_lora_sft_otfq.yaml
+llamafactory-cli train examples/train_qlora/qwen3_lora_sft_otfq.yaml
 ```
 
 #### 在 NPU 上基于 4 比特 Bitsandbytes 量化进行指令监督微调
 
 ```bash
-llamafactory-cli train examples/train_qlora/llama3_lora_sft_bnb_npu.yaml
+llamafactory-cli train examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml
 ```
 
 #### 基于 4/8 比特 GPTQ 量化进行指令监督微调
@@ -163,20 +151,20 @@ llamafactory-cli train examples/train_qlora/llama3_lora_sft_aqlm.yaml
 #### 在单机上进行指令监督微调
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 #### 在多机上进行指令监督微调
 
 ```bash
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
-FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
+FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
 ```
 
 #### 多模态指令监督微调
 
 ```bash
-FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3vl_full_sft.yaml
 ```
 
 ### 合并 LoRA 适配器与模型量化
@@ -186,19 +174,19 @@ FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.y
 注：请勿使用量化后的模型或 `quantization_bit` 参数来合并 LoRA 适配器。
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
 ```
 
 #### 使用 AutoGPTQ 量化模型
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
+llamafactory-cli export examples/merge_lora/qwen3_gptq.yaml
 ```
 
 ### 保存 Ollama 配置文件
 
 ```bash
-llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_full_sft.yaml
 ```
 
 ### 推理 LoRA 模型
@@ -206,26 +194,26 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
 #### 使用 vLLM 多卡推理评估
 
 ```
-python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
+python scripts/vllm_infer.py --model_name_or_path Qwen/Qwen3-4B-Instruct-2507 --template qwen3_nothink --dataset alpaca_en_demo
 python scripts/eval_bleu_rouge.py generated_predictions.jsonl
 ```
 
 #### 使用命令行对话框
 
 ```bash
-llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
 ```
 
 #### 使用浏览器对话框
 
 ```bash
-llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
+llamafactory-cli webchat examples/inference/qwen3_lora_sft.yaml
 ```
 
 #### 启动 OpenAI 风格 API
 
 ```bash
-llamafactory-cli api examples/inference/llama3_lora_sft.yaml
+llamafactory-cli api examples/inference/qwen3_lora_sft.yaml
 ```
 
 ### 杂项

examples/ascend/qwen3_full_sft_fsdp2.yaml

@@ -1,16 +1,22 @@
+# Start FSDP2 fine-tuning
+# accelerate launch \
+#     --config_file examples/accelerate/fsdp2_config.yaml \
+#     src/train.py examples/ascend/qwen3_full_sft_fsdp2.yaml
+# Change `num_processes` in fsdp2_config.yaml to 16 in A3
+
 ### model
-model_name_or_path: Qwen/Qwen3-32B
+model_name_or_path: Qwen/Qwen3-8B
 trust_remote_code: true
 use_v1_kernels: true
+flash_attn: fa2
 
 ### method
 stage: sft
 do_train: true
 finetuning_type: full
-deepspeed: examples/deepspeed/ds_z2_autotp_config.json
 
 ### dataset
-dataset: identity,alpaca_en_demo
+dataset: alpaca_en_demo
 template: qwen3
 cutoff_len: 2048
 max_samples: 1000
@@ -19,28 +25,21 @@ preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen3-32b/full/sft_autotp
+output_dir: saves/Qwen3-8B/full/sft
 logging_steps: 1
 save_steps: 500
+max_steps: 500
 plot_loss: true
 overwrite_output_dir: true
 save_only_model: false
 report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
 
 ### train
-per_device_train_batch_size: 4
+per_device_train_batch_size: 8
 gradient_accumulation_steps: 1
-learning_rate: 1.0e-4
+learning_rate: 1.0e-5
-num_train_epochs: 3.0
 lr_scheduler_type: cosine
 warmup_ratio: 0.1
 bf16: true
-ddp_timeout: 180000000
+ddp_timeout: 1800
 resume_from_checkpoint: null
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/ascend/qwen3moe_full_sft_fsdp.yaml

@@ -0,0 +1,46 @@
+# Start FSDP fine-tuning
+# accelerate launch \
+#     --config_file examples/accelerate/fsdp_config.yaml \
+#     src/train.py examples/ascend/qwen3moe_full_sft_fsdp.yaml
+# Change `num_processes` in fsdp_config.yaml to 16 in A3
+
+### model
+model_name_or_path: Qwen/Qwen3-30B-A3B-Instruct-2507
+trust_remote_code: true
+use_v1_kernels: true
+flash_attn: fa2
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+disable_gradient_checkpointing: false
+
+### dataset
+dataset: alpaca_zh
+template: qwen3
+cutoff_len: 1024
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/Qwen3-30B-A3B-Instruct-2507/full/sft
+logging_steps: 1
+save_steps: 500
+max_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: true
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 4
+gradient_accumulation_steps: 1
+learning_rate: 1.0e-4
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+seed: 1234

examples/ascend/qwen3vlmoe_full_sft_fsdp2.yaml

@@ -0,0 +1,48 @@
+# Start FSDP2 fine-tuning
+# accelerate launch \
+#     --config_file examples/accelerate/fsdp2_config.yaml \
+#     src/train.py examples/ascend/qwen3vlmoe_full_sft_fsdp2.yaml
+# Change `num_processes` in fsdp2_config.yaml to 16 in A3
+
+### model
+model_name_or_path: Qwen/Qwen3-VL-30B-A3B-Instruct
+image_max_pixels: 262144
+video_max_pixels: 16384
+trust_remote_code: true
+use_v1_kernels: true
+flash_attn: fa2
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+disable_gradient_checkpointing: false
+
+### dataset
+dataset: llava_1k_en, llava_1k_zh
+template: qwen3_vl
+cutoff_len: 1024
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/Qwen3-VL-30B-A3B-Instruct/full/sft
+logging_steps: 1
+save_steps: 500
+max_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: true
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 1
+learning_rate: 1.0e-4
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+seed: 1234

examples/inference/llama3_lora_sft.yaml

@@ -1,5 +0,0 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-adapter_name_or_path: saves/llama3-8b/lora/sft
-template: llama3
-infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
-trust_remote_code: true

examples/inference/qwen3.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
-template: qwen2_vl
+template: qwen3_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true

examples/inference/qwen3_full_sft.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: saves/llama3-8b/full/sft
+model_name_or_path: saves/qwen3-4b/full/sft
-template: llama3
+template: qwen3_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true

examples/inference/qwen3_lora_sft.yaml

@@ -0,0 +1,5 @@
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
+adapter_name_or_path: saves/qwen3-4b/lora/sft
+template: qwen3_nothink
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
+trust_remote_code: true

examples/inference/qwen3vl.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
-template: llama3
+template: qwen3_vl_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true

examples/merge_lora/qwen3_full_sft.yaml

@@ -1,10 +1,10 @@
 ### model
-model_name_or_path: saves/llama3-8b/full/sft
+model_name_or_path: saves/qwen3-4b/full/sft
-template: llama3
+template: qwen3_nothink
 trust_remote_code: true
 
 ### export
-export_dir: output/llama3_full_sft
+export_dir: saves/qwen3_sft_merged
 export_size: 5
 export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/merge_lora/qwen3_gptq.yaml

@@ -1,10 +1,10 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
-template: llama3
+template: qwen3_nothink
 trust_remote_code: true
 
 ### export
-export_dir: output/llama3_gptq
+export_dir: saves/qwen3_gptq
 export_quantization_bit: 4
 export_quantization_dataset: data/c4_demo.jsonl
 export_size: 5

examples/merge_lora/qwen3_lora_sft.yaml

@@ -1,13 +1,13 @@
 ### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
 
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
-adapter_name_or_path: saves/qwen2_5vl-7b/lora/sft
+adapter_name_or_path: saves/qwen3-4b/lora/sft
-template: qwen2_vl
+template: qwen3_nothink
 trust_remote_code: true
 
 ### export
-export_dir: output/qwen2_5vl_lora_sft
+export_dir: saves/qwen3_sft_merged
 export_size: 5
 export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/merge_lora/qwen3vl_lora_sft.yaml

@@ -1,13 +1,13 @@
 ### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
 
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
-adapter_name_or_path: saves/llama3-8b/lora/sft
+adapter_name_or_path: saves/qwen3-vl-4b/lora/sft
-template: llama3
+template: qwen3_vl_nothink
 trust_remote_code: true
 
 ### export
-export_dir: output/llama3_lora_sft
+export_dir: saves/qwen3_vl_sft_merged
 export_size: 5
 export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/requirements/adam-mini.txt

@@ -0,0 +1 @@
+adam-mini

examples/requirements/apollo.txt

@@ -0,0 +1 @@
+apollo-torch

examples/requirements/aqlm.txt

@@ -0,0 +1 @@
+aqlm[gpu]>=1.1.0

examples/requirements/badam.txt

@@ -0,0 +1 @@
+badam>=1.2.1

examples/requirements/bitsandbytes.txt

@@ -0,0 +1 @@
+bitsandbytes>=0.39.0

examples/requirements/eetq.txt

@@ -0,0 +1 @@
+eetq

examples/requirements/fp8-te.txt

@@ -0,0 +1,2 @@
+transformer_engine[pytorch]>=2.0.0
+accelerate>=1.10.0

examples/requirements/fp8.txt

@@ -0,0 +1,2 @@
+torchao>=0.8.0
+accelerate>=1.10.0

examples/requirements/galore.txt

@@ -0,0 +1 @@
+galore-torch

examples/requirements/gptq.txt

@@ -0,0 +1,2 @@
+optimum>=1.24.0
+gptqmodel>=2.0.0

examples/requirements/hqq.txt

@@ -0,0 +1 @@
+hqq

examples/requirements/liger-kernel.txt

@@ -0,0 +1 @@
+liger-kernel>=0.5.5

examples/requirements/minicpm-v.txt

@@ -0,0 +1,8 @@
+soundfile
+torchvision
+torchaudio
+vector_quantize_pytorch
+vocos
+msgpack
+referencing
+jsonschema_specifications

examples/requirements/openmind.txt

@@ -0,0 +1 @@
+openmind

examples/requirements/sglang.txt

@@ -0,0 +1,2 @@
+sglang[srt]>=0.4.5
+transformers==4.51.1

examples/requirements/swanlab.txt

@@ -0,0 +1 @@
+swanlab

examples/requirements/vllm.txt

@@ -0,0 +1 @@
+vllm>=0.4.3,<=0.11.0

examples/train_full/qwen3_full_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -10,15 +10,14 @@ deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json,
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/full/sft
+output_dir: saves/qwen3-4b/full/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_full/qwen3vl_full_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true
@@ -15,15 +15,14 @@ deepspeed: examples/deepspeed/ds_z3_config.json
 
 ### dataset
 dataset: mllm_demo,identity,alpaca_en_demo
-template: qwen2_vl
+template: qwen3_vl_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen2_5vl-7b/full/sft
+output_dir: saves/qwen3-vl-4b/full/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/llama3_lora_eval.yaml

@@ -1,19 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-adapter_name_or_path: saves/llama3-8b/lora/sft
-trust_remote_code: true
-
-### method
-finetuning_type: lora
-
-### dataset
-task: mmlu_test  # choices: [mmlu_test, ceval_validation, cmmlu_test]
-template: fewshot
-lang: en
-n_shot: 5
-
-### output
-save_dir: saves/llama3-8b/lora/eval
-
-### eval
-batch_size: 4

examples/train_lora/llama3_lora_ppo.yaml

@@ -1,43 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-reward_model: saves/llama3-8b/lora/reward
-trust_remote_code: true
-
-### method
-stage: ppo
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity,alpaca_en_demo
-template: llama3
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama3-8b/lora/ppo
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-5
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-
-### generate
-max_new_tokens: 512
-top_k: 0
-top_p: 0.9

examples/train_lora/llama3_lora_sft.yaml

@@ -1,46 +0,0 @@
-### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: identity,alpaca_en_demo
-template: llama3
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama3-8b/lora/sft
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/llama4_lora_sft_ds3.yaml

@@ -1,49 +0,0 @@
-# pip install git+https://github.com/hiyouga/transformers.git@llama4_train
-
-### model
-model_name_or_path: meta-llama/Llama-4-Scout-17B-16E-Instruct
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
-
-### dataset
-dataset: mllm_demo,identity,alpaca_en_demo
-template: llama4
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llama4-8b/lora/sft
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 2
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### eval
-# eval_dataset: alpaca_en_demo
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/qwen3_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -13,15 +13,14 @@ pref_loss: sigmoid  # choices: [sigmoid (dpo), orpo, simpo]
 
 ### dataset
 dataset: dpo_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/dpo
+output_dir: saves/qwen3-4b/lora/dpo
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_kto.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -12,15 +12,14 @@ pref_beta: 0.1
 
 ### dataset
 dataset: kto_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/kto
+output_dir: saves/qwen3-4b/lora/kto
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_pretrain.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -13,12 +13,11 @@ lora_target: all
 dataset: c4_demo
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/pretrain
+output_dir: saves/qwen3-4b/lora/pretrain
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_reward.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,15 +11,14 @@ lora_target: all
 
 ### dataset
 dataset: dpo_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/reward
+output_dir: saves/qwen3-4b/lora/reward
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft.sh

@@ -2,7 +2,7 @@
 
 set -x
 
-MODEL_PATH=meta-llama/Meta-Llama-3-8B-Instruct
+MODEL_PATH=Qwen/Qwen3-4B-Instruct-2507
 
 llamafactory-cli train \
     --model_name_or_path ${MODEL_PATH} \
@@ -13,13 +13,12 @@ llamafactory-cli train \
     --lora_rank 8 \
     --lora_target all \
     --dataset identity,alpaca_en_demo \
-    --template llama3 \
+    --template qwen3_nothink \
     --cutoff_len 2048 \
     --max_samples 1000 \
-    --overwrite_cache \
     --preprocessing_num_workers 16 \
     --dataloader_num_workers 4 \
-    --output_dir saves/llama3-8b/lora/sft \
+    --output_dir saves/qwen3-4b/lora/sft \
     --logging_steps 10 \
     --save_steps 500 \
     --plot_loss \

examples/train_lora/qwen3_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: openai/gpt-oss-20b
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,15 +11,14 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: gpt
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/gpt-20b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft_ds3.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -12,15 +12,14 @@ deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json,
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3_lora_sft_ray.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct  # or use local absolute path
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507  # or use local absolute path
 trust_remote_code: true
 
 ### method
@@ -12,10 +12,9 @@ lora_target: all
 ### dataset
 dataset: identity,alpaca_en_demo
 dataset_dir: REMOTE:llamafactory/demo_data  # or use local absolute path
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
@@ -29,7 +28,7 @@ save_only_model: false
 report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
 
 ### ray
-ray_run_name: llama3_8b_sft_lora
+ray_run_name: qwen3_4b_sft_lora
 ray_storage_path: ./saves
 ray_num_workers: 4  # Number of GPUs to use.
 placement_strategy: PACK

examples/train_lora/qwen3_preprocess.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 trust_remote_code: true
 
 ### method
@@ -11,13 +11,12 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
-tokenized_path: saves/llama3-8b/dataset/sft
+tokenized_path: saves/qwen3-4b/dataset/sft
 
-### output
+### output (not used)
-output_dir: saves/llama3-8b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 overwrite_output_dir: true

examples/train_lora/qwen3vl_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true
@@ -15,15 +15,14 @@ pref_loss: sigmoid  # choices: [sigmoid (dpo), orpo, simpo]
 
 ### dataset
 dataset: rlhf_v
-template: qwen2_vl
+template: qwen3_vl_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen2_5vl-7b/lora/dpo
+output_dir: saves/qwen3-vl-4b/lora/dpo
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_lora/qwen3vl_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true
@@ -13,15 +13,14 @@ lora_target: all
 
 ### dataset
 dataset: mllm_demo,identity,alpaca_en_demo  # video: mllm_video_demo
-template: qwen2_vl
+template: qwen3_vl_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/qwen2_5vl-7b/lora/sft
+output_dir: saves/qwen3-vl-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_qlora/llama3_lora_sft_aqlm.yaml

@@ -14,7 +14,6 @@ dataset: identity,alpaca_en_demo
 template: llama3
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 

examples/train_qlora/llama3_lora_sft_awq.yaml

@@ -14,7 +14,6 @@ dataset: identity,alpaca_en_demo
 template: llama3
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 

examples/train_qlora/llama3_lora_sft_gptq.yaml

@@ -14,7 +14,6 @@ dataset: identity,alpaca_en_demo
 template: llama3
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 

examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 quantization_bit: 4
 quantization_method: bnb
 double_quantization: false
@@ -14,15 +14,14 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

examples/train_qlora/qwen3_lora_sft_otfq.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
 quantization_bit: 4  # choices: [8 (bnb/hqq/eetq), 4 (bnb/hqq), 3 (hqq), 2 (hqq)]
 quantization_method: bnb  # choices: [bnb, hqq, eetq]
 trust_remote_code: true
@@ -13,15 +13,14 @@ lora_target: all
 
 ### dataset
 dataset: identity,alpaca_en_demo
-template: llama3
+template: qwen3_nothink
 cutoff_len: 2048
 max_samples: 1000
-overwrite_cache: true
 preprocessing_num_workers: 16
 dataloader_num_workers: 4
 
 ### output
-output_dir: saves/llama3-8b/lora/sft
+output_dir: saves/qwen3-4b/lora/sft
 logging_steps: 10
 save_steps: 500
 plot_loss: true

pyproject.toml

@@ -1,42 +1,122 @@
 [build-system]
-requires = ["setuptools>=61.0"]
+requires = ["hatchling"]
-build-backend = "setuptools.build_meta"
+build-backend = "hatchling.build"
 
 [project]
 name = "llamafactory"
-requires-python = ">=3.9.0"
+dynamic = ["version"]
-dynamic = [
+description = "Unified Efficient Fine-Tuning of 100+ LLMs"
-    "version",
+readme = "README.md"
-    "dependencies",
+license = "Apache-2.0"
-    "optional-dependencies",
+requires-python = ">=3.11.0"
-    "scripts",
+authors = [
-    "authors",
+    { name = "hiyouga", email = "hiyouga@buaa.edu.cn" }
-    "description",
+]
-    "readme",
+keywords = [
-    "license",
+    "AI",
-    "keywords",
+    "LLM",
-    "classifiers"
+    "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 :: 3.10",
+    "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,<=4.57.1,!=4.52.0,!=4.57.0",
+    "datasets>=2.16.0,<=4.0.0",
+    "accelerate>=1.3.0,<=1.11.0",
+    "peft>=0.14.0,<=0.17.1",
+    "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",
+    "fire",
+    "omegaconf",
+    "packaging",
+    "protobuf",
+    "pyyaml",
+    "pydantic",
+    # api
+    "uvicorn",
+    "fastapi",
+    "sse-starlette"
 ]
 
+[project.optional-dependencies]
+dev = ["pre-commit", "ruff", "pytest", "build"]
+metrics = ["nltk", "jieba", "rouge-chinese"]
+deepspeed = ["deepspeed>=0.10.0,<=0.16.9"]
+
+[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 = "py39"
+target-version = "py311"
 line-length = 119
 indent-width = 4
 
 [tool.ruff.lint]
 ignore = [
-    "C408", # collection
+    "C408",  # collection
-    "C901", # complex
+    "C901",  # complex
-    "E501", # line too long
+    "E501",  # line too long
-    "E731", # lambda function
+    "E731",  # lambda function
-    "E741", # ambiguous var name
+    "E741",  # ambiguous var name
-    "D100", # no doc public module
+    "UP007", # no upgrade union
-    "D101", # no doc public class
+    "UP045", # no upgrade optional
-    "D102", # no doc public method
+    "D100",  # no doc public module
-    "D103", # no doc public function
+    "D101",  # no doc public class
-    "D104", # no doc public package
+    "D102",  # no doc public method
-    "D105", # no doc magic method
+    "D103",  # no doc public function
-    "D107", # no doc __init__
+    "D104",  # no doc public package
+    "D105",  # no doc magic method
+    "D107",  # no doc __init__
 ]
 extend-select = [
     "C",      # complexity
@@ -73,23 +153,3 @@ indent-style = "space"
 docstring-code-format = true
 skip-magic-trailing-comma = false
 line-ending = "auto"
-
-[tool.uv]
-conflicts = [
-    [
-        { extra = "torch-npu" },
-        { extra = "aqlm" },
-    ],
-    [
-        { extra = "torch-npu" },
-        { extra = "vllm" },
-    ],
-    [
-        { extra = "torch-npu" },
-        { extra = "sglang" },
-    ],
-    [
-        { extra = "vllm" },
-        { extra = "sglang" },
-    ],
-]

requirements.txt

@@ -1,38 +0,0 @@
-# core deps
-transformers>=4.49.0,<=4.56.2,!=4.52.0; python_version < '3.10'
-transformers>=4.49.0,<=4.57.3,!=4.52.0,!=4.57.0; python_version >= '3.10'
-datasets>=2.16.0,<=4.0.0
-accelerate>=1.3.0,<=1.11.0
-peft>=0.14.0,<=0.17.1
-trl>=0.8.6,<=0.9.6
-# gui
-gradio>=4.38.0,<=5.45.0
-matplotlib>=3.7.0
-tyro<0.9.0
-# ops
-einops
-numpy<2.0.0
-pandas>=2.0.0
-scipy
-# model and tokenizer
-sentencepiece
-tiktoken
-modelscope>=1.14.0
-hf-transfer
-safetensors<=0.5.3
-# python
-fire
-omegaconf
-packaging
-protobuf
-pyyaml
-pydantic<=2.10.6
-# api
-uvicorn
-fastapi
-sse-starlette
-# media
-av
-librosa
-# yanked
-propcache!=0.4.0

scripts/megatron_merge.py

@@ -16,7 +16,6 @@
 # limitations under the License.
 
 import os
-from typing import Optional
 
 import fire
 import torch
@@ -34,7 +33,7 @@ def convert_mca_to_hf(
     output_path: str = "./output",
     bf16: bool = False,
     fp16: bool = False,
-    convert_model_max_length: Optional[int] = None,
+    convert_model_max_length: int | None = None,
 ):
     """Convert megatron checkpoint to HuggingFace format.
 
@@ -67,11 +66,11 @@ def convert(
     output_path: str = "./output",
     bf16: bool = False,
     fp16: bool = False,
-    convert_model_max_length: Optional[int] = None,
+    convert_model_max_length: int | None = None,
     tensor_model_parallel_size: int = 1,
     pipeline_model_parallel_size: int = 1,
     expert_model_parallel_size: int = 1,
-    virtual_pipeline_model_parallel_size: Optional[int] = None,
+    virtual_pipeline_model_parallel_size: int | None = None,
 ):
     """Convert checkpoint between MCA and HuggingFace formats.
 

scripts/stat_utils/cal_ppl.py

@@ -14,7 +14,7 @@
 
 import json
 from dataclasses import dataclass
-from typing import Any, Literal, Optional
+from typing import Any, Literal
 
 import fire
 import torch
@@ -61,7 +61,7 @@ def calculate_ppl(
     dataset_dir: str = "data",
     template: str = "default",
     cutoff_len: int = 2048,
-    max_samples: Optional[int] = None,
+    max_samples: int | None = None,
     train_on_prompt: bool = False,
 ):
     r"""Calculate the ppl on the dataset of the pre-trained models.

scripts/vllm_infer.py

@@ -14,10 +14,12 @@
 
 import gc
 import json
-from typing import Optional
+import time
 
 import av
 import fire
+from datasets import load_dataset
+from eval_bleu_rouge import compute_metrics
 from tqdm import tqdm
 from transformers import Seq2SeqTrainingArguments
 
@@ -49,18 +51,19 @@ def vllm_infer(
     dataset_dir: str = "data",
     template: str = "default",
     cutoff_len: int = 2048,
-    max_samples: Optional[int] = None,
+    max_samples: int | None = None,
     vllm_config: str = "{}",
     save_name: str = "generated_predictions.jsonl",
+    matrix_save_name: str = None,
     temperature: float = 0.95,
     top_p: float = 0.7,
     top_k: int = 50,
     max_new_tokens: int = 1024,
     repetition_penalty: float = 1.0,
     skip_special_tokens: bool = True,
-    default_system: Optional[str] = None,
+    default_system: str | None = None,
     enable_thinking: bool = True,
-    seed: Optional[int] = None,
+    seed: int | None = None,
     pipeline_parallel_size: int = 1,
     image_max_pixels: int = 768 * 768,
     image_min_pixels: int = 32 * 32,
@@ -118,6 +121,7 @@ def vllm_infer(
     if isinstance(model_args.vllm_config, dict):
         engine_args.update(model_args.vllm_config)
 
+    model_preparation_start_time = time.time()
     llm = LLM(**engine_args)
 
     # load datasets
@@ -143,6 +147,7 @@ def vllm_infer(
     all_prompts, all_preds, all_labels = [], [], []
     need_video_kwargs = _need_video_kwargs(template)
 
+    model_predict_start_time = time.time()
     # Add batch process to avoid the issue of too many files opened
     for i in tqdm(range(0, len(train_dataset), batch_size), desc="Processing batched inference"):
         vllm_inputs, prompts, labels = [], [], []
@@ -219,6 +224,7 @@ def vllm_infer(
         all_labels.extend(labels)
         gc.collect()
 
+    model_predict_end_time = time.time()
     # Write all results at once outside the loop
     with open(save_name, "w", encoding="utf-8") as f:
         for text, pred, label in zip(all_prompts, all_preds, all_labels):
@@ -228,6 +234,49 @@ def vllm_infer(
     print(f"{len(all_prompts)} total generated results have been saved at {save_name}.")
     print("*" * 70)
 
+    # Write all matrix results when matrix_save_name is not None,
+    # The result matrix is referencing src.llamafactory.train.sft.workflow.run_sft # 127~132
+    # trainer.save_metrics("predict", predict_results.metrics)
+    #
+    #   {
+    #        "predict_bleu-4": 4.349975,
+    #        "predict_model_preparation_time": 0.0128,
+    #        "predict_rouge-1": 21.873359375,
+    #        "predict_rouge-2": 4.144340625,
+    #        "predict_rouge-l": 10.83949375,
+    #        "predict_runtime": 131.664,
+    #        "predict_samples_per_second": 0.076,
+    #        "predict_steps_per_second": 0.008
+    #    }
+    #
+    if matrix_save_name is not None:
+        predict_time = model_predict_end_time - model_predict_start_time
+        preparation_time = model_predict_start_time - model_preparation_start_time
+
+        start_time = time.time()
+        dataset = load_dataset("json", data_files=save_name, split="train")
+        dataset = dataset.map(compute_metrics, num_proc=8, remove_columns=dataset.column_names)
+        score_dict = dataset.to_dict()
+
+        average_score = {}
+        for task, scores in sorted(score_dict.items(), key=lambda x: x[0]):
+            score = sum(scores) / len(scores) if scores else 0.0
+            print(f"predict_{task}: {score:.4f}")
+            average_score["predict_" + task] = score
+
+        average_score["predict_model_preparation_time"] = preparation_time
+        average_score["predict_runtime"] = predict_time
+        num_steps = len(range(0, len(train_dataset), batch_size))
+        average_score["predict_samples_per_second"] = len(dataset) / predict_time if predict_time > 0 else 0.0
+        average_score["predict_steps_per_second"] = num_steps / predict_time if predict_time > 0 else 0.0
+
+        with open(matrix_save_name, "w", encoding="utf-8") as f:
+            json.dump(average_score, f, indent=4)
+
+        print("*" * 70)
+        print(f"\nDone in {time.time() - start_time:.3f}s.\nScore file saved to {matrix_save_name}.")
+        print("*" * 70)
+
 
 if __name__ == "__main__":
     fire.Fire(vllm_infer)

setup.py

@@ -1,116 +0,0 @@
-# Copyright 2025 the LlamaFactory team.
-#
-# 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.
-
-import os
-import re
-
-from setuptools import find_packages, setup
-
-
-def get_version() -> str:
-    with open(os.path.join("src", "llamafactory", "extras", "env.py"), encoding="utf-8") as f:
-        file_content = f.read()
-        pattern = r"{}\W*=\W*\"([^\"]+)\"".format("VERSION")
-        (version,) = re.findall(pattern, file_content)
-        return version
-
-
-def get_requires() -> list[str]:
-    with open("requirements.txt", encoding="utf-8") as f:
-        file_content = f.read()
-        lines = [line.strip() for line in file_content.strip().split("\n") if not line.startswith("#")]
-        return lines
-
-
-def get_console_scripts() -> list[str]:
-    console_scripts = ["llamafactory-cli = llamafactory.cli:main"]
-    if os.getenv("ENABLE_SHORT_CONSOLE", "1").lower() in ["true", "y", "1"]:
-        console_scripts.append("lmf = llamafactory.cli:main")
-
-    return console_scripts
-
-
-extra_require = {
-    "torch": ["torch>=2.0.0", "torchvision>=0.15.0"],
-    "torch-npu": ["torch==2.7.1", "torch-npu==2.7.1", "torchvision==0.22.1", "decorator"],
-    "metrics": ["nltk", "jieba", "rouge-chinese"],
-    "deepspeed": ["deepspeed>=0.10.0,<=0.16.9"],
-    "liger-kernel": ["liger-kernel>=0.5.5"],
-    "bitsandbytes": ["bitsandbytes>=0.39.0"],
-    "hqq": ["hqq"],
-    "eetq": ["eetq"],
-    "gptq": ["optimum>=1.24.0", "gptqmodel>=2.0.0"],
-    "aqlm": ["aqlm[gpu]>=1.1.0"],
-    "vllm": ["vllm>=0.4.3,<=0.11.0"],
-    "sglang": ["sglang[srt]>=0.4.5", "transformers==4.51.1"],
-    "galore": ["galore-torch"],
-    "apollo": ["apollo-torch"],
-    "badam": ["badam>=1.2.1"],
-    "adam-mini": ["adam-mini"],
-    "minicpm_v": [
-        "soundfile",
-        "torchvision",
-        "torchaudio",
-        "vector_quantize_pytorch",
-        "vocos",
-        "msgpack",
-        "referencing",
-        "jsonschema_specifications",
-    ],
-    "openmind": ["openmind"],
-    "swanlab": ["swanlab"],
-    "fp8": ["torchao>=0.8.0", "accelerate>=1.10.0"],
-    "fp8-te": ["transformer_engine[pytorch]>=2.0.0", "accelerate>=1.10.0"],
-    "fp8-all": ["torchao>=0.8.0", "transformer_engine[pytorch]>=2.0.0", "accelerate>=1.10.0"],
-    "dev": ["pre-commit", "ruff", "pytest", "build"],
-}
-
-
-def main():
-    setup(
-        name="llamafactory",
-        version=get_version(),
-        author="hiyouga",
-        author_email="hiyouga@buaa.edu.cn",
-        description="Unified Efficient Fine-Tuning of 100+ LLMs",
-        long_description=open("README.md", encoding="utf-8").read(),
-        long_description_content_type="text/markdown",
-        keywords=["AI", "LLM", "GPT", "ChatGPT", "Llama", "Transformer", "DeepSeek", "Pytorch"],
-        license="Apache 2.0 License",
-        url="https://github.com/hiyouga/LLaMA-Factory",
-        package_dir={"": "src"},
-        packages=find_packages("src"),
-        python_requires=">=3.9.0",
-        install_requires=get_requires(),
-        extras_require=extra_require,
-        entry_points={"console_scripts": get_console_scripts()},
-        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 :: 3.9",
-            "Programming Language :: Python :: 3.10",
-            "Programming Language :: Python :: 3.11",
-            "Programming Language :: Python :: 3.12",
-            "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        ],
-    )
-
-
-if __name__ == "__main__":
-    main()

src/llamafactory/api/app.py

@@ -16,7 +16,7 @@ import asyncio
 import os
 from contextlib import asynccontextmanager
 from functools import partial
-from typing import Annotated, Optional
+from typing import Annotated
 
 from ..chat import ChatModel
 from ..extras.constants import EngineName
@@ -79,7 +79,7 @@ def create_app(chat_model: "ChatModel") -> "FastAPI":
     api_key = os.getenv("API_KEY")
     security = HTTPBearer(auto_error=False)
 
-    async def verify_api_key(auth: Annotated[Optional[HTTPAuthorizationCredentials], Depends(security)]):
+    async def verify_api_key(auth: Annotated[HTTPAuthorizationCredentials | None, Depends(security)]):
         if api_key and (auth is None or auth.credentials != api_key):
             raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid API key.")
 

src/llamafactory/api/protocol.py

@@ -14,10 +14,9 @@
 
 import time
 from enum import Enum, unique
-from typing import Any, Optional, Union
+from typing import Any, Literal
 
 from pydantic import BaseModel, Field
-from typing_extensions import Literal
 
 
 @unique
@@ -61,7 +60,7 @@ class FunctionDefinition(BaseModel):
 
 class FunctionAvailable(BaseModel):
     type: Literal["function", "code_interpreter"] = "function"
-    function: Optional[FunctionDefinition] = None
+    function: FunctionDefinition | None = None
 
 
 class FunctionCall(BaseModel):
@@ -77,35 +76,35 @@ class URL(BaseModel):
 
 class MultimodalInputItem(BaseModel):
     type: Literal["text", "image_url", "video_url", "audio_url"]
-    text: Optional[str] = None
+    text: str | None = None
-    image_url: Optional[URL] = None
+    image_url: URL | None = None
-    video_url: Optional[URL] = None
+    video_url: URL | None = None
-    audio_url: Optional[URL] = None
+    audio_url: URL | None = None
 
 
 class ChatMessage(BaseModel):
     role: Role
-    content: Optional[Union[str, list[MultimodalInputItem]]] = None
+    content: str | list[MultimodalInputItem] | None = None
-    tool_calls: Optional[list[FunctionCall]] = None
+    tool_calls: list[FunctionCall] | None = None
 
 
 class ChatCompletionMessage(BaseModel):
-    role: Optional[Role] = None
+    role: Role | None = None
-    content: Optional[str] = None
+    content: str | None = None
-    tool_calls: Optional[list[FunctionCall]] = None
+    tool_calls: list[FunctionCall] | None = None
 
 
 class ChatCompletionRequest(BaseModel):
     model: str
     messages: list[ChatMessage]
-    tools: Optional[list[FunctionAvailable]] = None
+    tools: list[FunctionAvailable] | None = None
-    do_sample: Optional[bool] = None
+    do_sample: bool | None = None
-    temperature: Optional[float] = None
+    temperature: float | None = None
-    top_p: Optional[float] = None
+    top_p: float | None = None
     n: int = 1
-    presence_penalty: Optional[float] = None
+    presence_penalty: float | None = None
-    max_tokens: Optional[int] = None
+    max_tokens: int | None = None
-    stop: Optional[Union[str, list[str]]] = None
+    stop: str | list[str] | None = None
     stream: bool = False
 
 
@@ -118,7 +117,7 @@ class ChatCompletionResponseChoice(BaseModel):
 class ChatCompletionStreamResponseChoice(BaseModel):
     index: int
     delta: ChatCompletionMessage
-    finish_reason: Optional[Finish] = None
+    finish_reason: Finish | None = None
 
 
 class ChatCompletionResponseUsage(BaseModel):
@@ -147,7 +146,7 @@ class ChatCompletionStreamResponse(BaseModel):
 class ScoreEvaluationRequest(BaseModel):
     model: str
     messages: list[str]
-    max_length: Optional[int] = None
+    max_length: int | None = None
 
 
 class ScoreEvaluationResponse(BaseModel):

src/llamafactory/chat/hf_engine.py

@@ -14,9 +14,9 @@
 
 import asyncio
 import os
-from collections.abc import AsyncGenerator
+from collections.abc import AsyncGenerator, Callable
 from threading import Thread
-from typing import TYPE_CHECKING, Any, Callable, Optional, Union
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 import torch
 from transformers import GenerationConfig, TextIteratorStreamer

src/llamafactory/data/converter.py

@@ -15,7 +15,7 @@ import json
 import os
 from abc import abstractmethod
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any, Optional, Union
+from typing import TYPE_CHECKING, Any, Union
 
 from ..extras import logging
 from .data_utils import Role
@@ -40,7 +40,7 @@ class DatasetConverter:
     dataset_attr: "DatasetAttr"
     data_args: "DataArguments"
 
-    def _find_medias(self, medias: Union["MediaType", list["MediaType"], None]) -> Optional[list["MediaType"]]:
+    def _find_medias(self, medias: Union["MediaType", list["MediaType"], None]) -> list["MediaType"] | None:
         r"""Optionally concatenate media path to media dir when loading from local disk."""
         if medias is None:
             return None