release v0.8.0

Former-commit-id: 004db680b9e3996ec511ee818df6c0c02bf13603

.dockerignore

@@ -4,6 +4,8 @@
 .venv
 cache
 data
+hf_cache
+output
 examples
 .dockerignore
 .gitattributes

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -13,6 +13,18 @@ body:
         - label: I have read the README and searched the existing issues.
           required: true
 
+  - type: textarea
+    id: system-info
+    validations:
+      required: true
+    attributes:
+      label: System Info
+      description: |
+        Please share your system info with us. You can run the command **llamafactory-cli env** and copy-paste its output below.
+        请提供您的系统信息。您可以在命令行运行 **llamafactory-cli env** 并将其输出复制到该文本框中。
+
+      placeholder: llamafactory version, platform, python version, ...
+
   - type: textarea
     id: reproduction
     validations:
@@ -26,7 +38,7 @@ body:
         请合理使用 Markdown 标签来格式化您的文本。
 
       placeholder: |
-        python src/train_bash.py ...
+        llamafactory-cli train ...
 
   - type: textarea
     id: expected-behavior
@@ -38,18 +50,6 @@ body:
         Please provide a clear and concise description of what you would expect to happen.
         请提供您原本的目的，即这段代码的期望行为。
 
-  - type: textarea
-    id: system-info
-    validations:
-      required: false
-    attributes:
-      label: System Info
-      description: |
-        Please share your system info with us. You can run the command **transformers-cli env** and copy-paste its output below.
-        请提供您的系统信息。您可以在命令行运行 **transformers-cli env** 并将其输出复制到该文本框中。
-
-      placeholder: transformers version, platform, python version, ...
-
   - type: textarea
     id: others
     validations:

.github/workflows/tests.yml

@@ -2,28 +2,38 @@ name: tests
 
 on:
   push:
-    branches: [ "main" ]
+    branches:
+      - main
+    paths:
+      - "**.py"
+      - "requirements.txt"
+      - ".github/workflows/*.yml"
   pull_request:
-    branches: [ "main" ]
+    branches:
+      - main
+    paths:
+      - "**.py"
+      - "requirements.txt"
+      - ".github/workflows/*.yml"
 
 jobs:
-  check_code_quality:
-
+  tests:
     runs-on: ubuntu-latest
-
     steps:
       - uses: actions/checkout@v4
-
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: "3.8"
-
+          cache: "pip"
+          cache-dependency-path: "setup.py"
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install ruff
-
+          python -m pip install .[torch,dev]
       - name: Check quality
         run: |
-            make style && make quality
+          make style && make quality
+      - name: Test with pytest
+        run: |
+          make test

Dockerfile

@@ -6,9 +6,9 @@ COPY requirements.txt /app/
 RUN pip install -r requirements.txt
 
 COPY . /app/
-RUN pip install -e .[deepspeed,metrics,bitsandbytes,qwen]
+RUN pip install -e .[metrics,bitsandbytes,qwen]
 
 VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
 EXPOSE 7860
 
-CMD [ "python", "src/train_web.py" ]
+CMD [ "llamafactory-cli", "webui" ]

Makefile

@@ -1,4 +1,4 @@
-.PHONY: quality style
+.PHONY: quality style test
 
 check_dirs := scripts src tests
 
@@ -9,3 +9,6 @@ quality:
 style:
 	ruff check $(check_dirs) --fix
 	ruff format $(check_dirs)
+
+test:
+	pytest tests/

README.md

@@ -3,15 +3,17 @@
 [![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)
 [![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)
 [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)
-[![PyPI](https://img.shields.io/pypi/v/llmtuner)](https://pypi.org/project/llmtuner/)
-[![Downloads](https://static.pepy.tech/badge/llmtuner)](https://pypi.org/project/llmtuner/)
-[![Citation](https://img.shields.io/badge/citation-34-green)](#projects-using-llama-factory)
+[![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
+[![Citation](https://img.shields.io/badge/citation-44-green)](#projects-using-llama-factory)
 [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
 [![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)
 [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)
+[![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)
 [![Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
 [![Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)
+
+[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)
 
 👋 Join our [WeChat](assets/wechat.jpg).
 
@@ -24,6 +26,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/9840a653-7e9c-41c8-ae89
 Choose your path:
 
 - **Colab**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing
+- **PAI-DSW**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
 - **Local machine**: Please refer to [usage](#getting-started)
 
 ## Table of Contents
@@ -43,8 +46,8 @@ Choose your path:
 
 ## Features
 
-- **Various models**: LLaMA, Mistral, Mixtral-MoE, Qwen, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
-- **Integrated methods**: (Continuous) pre-training, supervised fine-tuning, reward modeling, PPO, DPO and ORPO.
+- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
+- **Integrated methods**: (Continuous) pre-training, (multimodal) supervised fine-tuning, reward modeling, PPO, DPO, KTO, ORPO, etc.
 - **Scalable resources**: 32-bit full-tuning, 16-bit freeze-tuning, 16-bit LoRA and 2/4/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8.
 - **Advanced algorithms**: GaLore, BAdam, DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ and Agent tuning.
 - **Practical tricks**: FlashAttention-2, Unsloth, RoPE scaling, NEFTune and rsLoRA.
@@ -68,55 +71,69 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 ## Changelog
 
-[24/04/21] We supported **[Mixture-of-Depths](https://arxiv.org/abs/2404.02258)** according to [AstraMindAI's implementation](https://github.com/astramind-ai/Mixture-of-depths). See `examples/extras/mod` for usage.
+[24/06/07] We supported fine-tuning the **[Qwen-2](https://qwenlm.github.io/blog/qwen2/)** series models.
 
-[24/04/19] We supported **Meta Llama 3** model series.
+[24/06/05] We supported fine-tuning the **[GLM-4-9B/GLM-4-9B-Chat](https://github.com/THUDM/GLM-4)** models.
 
-[24/04/16] We supported **[BAdam](https://arxiv.org/abs/2404.02827)**. See `examples/extras/badam` for usage.
-
-[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).
+[24/05/26] We supported **[SimPO](https://arxiv.org/abs/2405.14734)** algorithm for preference learning. See [examples](examples/README.md) for usage.
 
 <details><summary>Full Changelog</summary>
 
-[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See `examples/lora_single_gpu` for usage.
+[24/05/20] We supported fine-tuning the **PaliGemma** series models. Note that the PaliGemma models are pre-trained models, you need to fine-tune them with `gemma` template for chat completion.
+
+[24/05/18] We supported **[KTO](https://arxiv.org/abs/2402.01306)** algorithm for preference learning. See [examples](examples/README.md) for usage.
+
+[24/05/14] We supported training and inference on the Ascend NPU devices. Check [installation](#installation) section for details.
+
+[24/04/26] We supported fine-tuning the **LLaVA-1.5** multimodal LLMs. See [examples](examples/README.md) for usage.
+
+[24/04/22] We provided a **[Colab notebook](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)** for fine-tuning the Llama-3 model on a free T4 GPU. Two Llama-3-derived models fine-tuned using LLaMA Factory are available at Hugging Face, check [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) and [Llama3-Chinese](https://huggingface.co/zhichen/Llama3-Chinese) for details.
+
+[24/04/21] We supported **[Mixture-of-Depths](https://arxiv.org/abs/2404.02258)** according to [AstraMindAI's implementation](https://github.com/astramind-ai/Mixture-of-depths). See [examples](examples/README.md) for usage.
+
+[24/04/16] We supported **[BAdam](https://arxiv.org/abs/2404.02827)**. See [examples](examples/README.md) for usage.
+
+[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).
+
+[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See [examples](examples/README.md) for usage.
 
 [24/03/21] Our paper "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" is available at arXiv!
 
-[24/03/20] We supported **FSDP+QLoRA** that fine-tunes a 70B model on 2x24GB GPUs. See `examples/extras/fsdp_qlora` for usage.
+[24/03/20] We supported **FSDP+QLoRA** that fine-tunes a 70B model on 2x24GB GPUs. See [examples](examples/README.md) for usage.
 
-[24/03/13] We supported **[LoRA+](https://arxiv.org/abs/2402.12354)**. See `examples/extras/loraplus` for usage.
+[24/03/13] We supported **[LoRA+](https://arxiv.org/abs/2402.12354)**. See [examples](examples/README.md) for usage.
 
-[24/03/07] We supported gradient low-rank projection (**[GaLore](https://arxiv.org/abs/2403.03507)**) algorithm. See `examples/extras/galore` for usage.
+[24/03/07] We supported gradient low-rank projection (**[GaLore](https://arxiv.org/abs/2403.03507)**) algorithm. See [examples](examples/README.md) for usage.
 
-[24/03/07] We integrated **[vLLM](https://github.com/vllm-project/vllm)** for faster and concurrent inference. Try `--infer_backend vllm` to enjoy **270%** inference speed. (LoRA is not yet supported, merge it first.)
+[24/03/07] We integrated **[vLLM](https://github.com/vllm-project/vllm)** for faster and concurrent inference. Try `infer_backend: vllm` to enjoy **270%** inference speed.
 
-[24/02/28] We supported weight-decomposed LoRA (**[DoRA](https://arxiv.org/abs/2402.09353)**). Try `--use_dora` to activate DoRA training.
+[24/02/28] We supported weight-decomposed LoRA (**[DoRA](https://arxiv.org/abs/2402.09353)**). Try `use_dora: true` to activate DoRA training.
 
-[24/02/15] We supported **block expansion** proposed by [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro). See `examples/extras/llama_pro` for usage.
+[24/02/15] We supported **block expansion** proposed by [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro). See [examples](examples/README.md) for usage.
 
 [24/02/05] Qwen1.5 (Qwen2 beta version) series models are supported in LLaMA-Factory. Check this [blog post](https://qwenlm.github.io/blog/qwen1.5/) for details.
 
-[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `--dataset glaive_toolcall`.
+[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `dataset: glaive_toolcall_en`.
 
-[23/12/23] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s implementation to boost LoRA tuning for the LLaMA, Mistral and Yi models. Try `--use_unsloth` argument to activate unsloth patch. It achieves **170%** speed in our benchmark, check [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison) for details.
+[23/12/23] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s implementation to boost LoRA tuning for the LLaMA, Mistral and Yi models. Try `use_unsloth: true` argument to activate unsloth patch. It achieves **170%** speed in our benchmark, check [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison) for details.
 
 [23/12/12] We supported fine-tuning the latest MoE model **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)** in our framework. See hardware requirement [here](#hardware-requirement).
 
-[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)** for Chinese mainland users. See [this tutorial](#use-modelscope-hub-optional) for usage.
+[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelscope-hub) for usage.
 
-[23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `--neftune_noise_alpha` argument to activate NEFTune, e.g., `--neftune_noise_alpha 5`.
+[23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `neftune_noise_alpha: 5` argument to activate NEFTune.
 
-[23/09/27] We supported **$S^2$-Attn** proposed by [LongLoRA](https://github.com/dvlab-research/LongLoRA) for the LLaMA models. Try `--shift_attn` argument to enable shift short attention.
+[23/09/27] We supported **$S^2$-Attn** proposed by [LongLoRA](https://github.com/dvlab-research/LongLoRA) for the LLaMA models. Try `shift_attn: true` argument to enable shift short attention.
 
-[23/09/23] We integrated MMLU, C-Eval and CMMLU benchmarks in this repo. See [this example](#evaluation) to evaluate your models.
+[23/09/23] We integrated MMLU, C-Eval and CMMLU benchmarks in this repo. See [examples](examples/README.md) for usage.
 
-[23/09/10] We supported **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**. Try `--flash_attn` argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs.
+[23/09/10] We supported **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**. Try `flash_attn: fa2` argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs.
 
-[23/08/12] We supported **RoPE scaling** to extend the context length of the LLaMA models. Try `--rope_scaling linear` argument in training and `--rope_scaling dynamic` argument at inference to extrapolate the position embeddings.
+[23/08/12] We supported **RoPE scaling** to extend the context length of the LLaMA models. Try `rope_scaling: linear` argument in training and `rope_scaling: dynamic` argument at inference to extrapolate the position embeddings.
 
-[23/08/11] We supported **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [this example](#dpo-training) to train your models.
+[23/08/11] We supported **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [examples](examples/README.md) for usage.
 
-[23/07/31] We supported **dataset streaming**. Try `--streaming` and `--max_steps 10000` arguments to load your dataset in streaming mode.
+[23/07/31] We supported **dataset streaming**. Try `streaming: true` and `max_steps: 10000` arguments to load your dataset in streaming mode.
 
 [23/07/29] We released two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)) for details.
 
@@ -128,44 +145,50 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 [23/06/22] We aligned the [demo API](src/api_demo.py) with the [OpenAI's](https://platform.openai.com/docs/api-reference/chat) format where you can insert the fine-tuned model in **arbitrary ChatGPT-based applications**.
 
-[23/06/03] We supported quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). Try `--quantization_bit 4/8` argument to work with quantized models.
+[23/06/03] We supported quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). See [examples](examples/README.md) for usage.
 
 </details>
 
 ## Supported Models
 
-| Model                                                    | Model size                  | Default module    | Template  |
-| -------------------------------------------------------- | --------------------------- | ----------------- | --------- |
-| [Baichuan2](https://huggingface.co/baichuan-inc)         | 7B/13B                      | W_pack            | baichuan2 |
-| [BLOOM](https://huggingface.co/bigscience)               | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value   | -         |
-| [BLOOMZ](https://huggingface.co/bigscience)              | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value   | -         |
-| [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                          | query_key_value   | chatglm3  |
-| [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                    | q_proj,v_proj     | cohere    |
-| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B                  | q_proj,v_proj     | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                 | query_key_value   | falcon    |
-| [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                       | q_proj,v_proj     | gemma     |
-| [InternLM2](https://huggingface.co/internlm)             | 7B/20B                      | wqkv              | intern2   |
-| [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B              | q_proj,v_proj     | -         |
-| [LLaMA-2](https://huggingface.co/meta-llama)             | 7B/13B/70B                  | q_proj,v_proj     | llama2    |
-| [LLaMA-3](https://huggingface.co/meta-llama)             | 8B/70B                      | q_proj,v_proj     | llama3    |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B               | q_proj,v_proj     | mistral   |
-| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                       | att_proj          | olmo      |
-| [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                   | q_proj,v_proj     | -         |
-| [Qwen](https://huggingface.co/Qwen)                      | 1.8B/7B/14B/72B             | c_attn            | qwen      |
-| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B | q_proj,v_proj     | qwen      |
-| [StarCoder2](https://huggingface.co/bigcode)             | 3B/7B/15B                   | q_proj,v_proj     | -         |
-| [XVERSE](https://huggingface.co/xverse)                  | 7B/13B/65B                  | q_proj,v_proj     | xverse    |
-| [Yi](https://huggingface.co/01-ai)                       | 6B/9B/34B                   | q_proj,v_proj     | yi        |
-| [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                 | q_proj,v_proj     | yuan      |
+| Model                                                    | Model size                       | Template  |
+| -------------------------------------------------------- | -------------------------------- | --------- |
+| [Baichuan2](https://huggingface.co/baichuan-inc)         | 7B/13B                           | baichuan2 |
+| [BLOOM](https://huggingface.co/bigscience)               | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
+| [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 (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek  |
+| [Falcon](https://huggingface.co/tiiuae)                  | 7B/11B/40B/180B                  | falcon    |
+| [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | gemma     |
+| [GLM4](https://huggingface.co/THUDM)                     | 9B                               | glm4      |
+| [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | intern2   |
+| [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B                   | -         |
+| [LLaMA-2](https://huggingface.co/meta-llama)             | 7B/13B/70B                       | llama2    |
+| [LLaMA-3](https://huggingface.co/meta-llama)             | 8B/70B                           | llama3    |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)             | 7B/13B                           | vicuna    |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B                    | mistral   |
+| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                            | -         |
+| [PaliGemma](https://huggingface.co/google)               | 3B                               | gemma     |
+| [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                        | -         |
+| [Phi-3](https://huggingface.co/microsoft)                | 4B/7B/14B                        | phi       |
+| [Qwen](https://huggingface.co/Qwen)                      | 1.8B/7B/14B/72B                  | qwen      |
+| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | qwen      |
+| [Qwen2 (MoE)](https://huggingface.co/Qwen)               | 0.5B/1.5B/7B/57B/72B             | qwen      |
+| [StarCoder2](https://huggingface.co/bigcode)             | 3B/7B/15B                        | -         |
+| [XVERSE](https://huggingface.co/xverse)                  | 7B/13B/65B                       | xverse    |
+| [Yi (1/1.5)](https://huggingface.co/01-ai)               | 6B/9B/34B                        | yi        |
+| [Yi-VL](https://huggingface.co/01-ai)                    | 6B/34B                           | yi_vl     |
+| [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                      | yuan      |
 
 > [!NOTE]
-> **Default module** is used for the `--lora_target` argument, you can use `--lora_target all` to specify all the available modules.
+> For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models.
 >
-> For the "base" models, the `--template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "chat" models.
+> Remember to use the **SAME** template in training and inference.
 
-Please refer to [constants.py](src/llmtuner/extras/constants.py) for a full list of models we supported.
+Please refer to [constants.py](src/llamafactory/extras/constants.py) for a full list of models we supported.
 
-You also can add a custom chat template to [template.py](src/llmtuner/data/template.py).
+You also can add a custom chat template to [template.py](src/llamafactory/data/template.py).
 
 ## Supported Training Approaches
 
@@ -176,7 +199,9 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 | Reward Modeling        | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | PPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | DPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| KTO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | ORPO Training          | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| SimPO Training         | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 
 ## Provided Datasets
 
@@ -189,6 +214,8 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
 - [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
 - [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
+- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
+- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
 - [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
 - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
 
@@ -196,12 +223,12 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 
 <details><summary>Supervised fine-tuning datasets</summary>
 
+- [Identity (en&zh)](data/identity.json)
 - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
-- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
+- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)
 - [Alpaca GPT4 (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
-- [Self Cognition (zh)](data/self_cognition.json)
-- [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
-- [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection)
+- [Glaive Function Calling V2 (en&zh)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
+- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
 - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
 - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
 - [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN)
@@ -210,7 +237,6 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
 - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
 - [UltraChat (en)](https://github.com/thunlp/UltraChat)
-- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
 - [OpenPlatypus (en)](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)
 - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
 - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
@@ -223,15 +249,17 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
 - [deepctrl (en&zh)](https://www.modelscope.cn/datasets/deepctrl/deepctrl-sft-data)
-- [Ad Gen (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
+- [Advertise Generating (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
 - [ShareGPT Hyperfiltered (en)](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k)
 - [ShareGPT4 (en&zh)](https://huggingface.co/datasets/shibing624/sharegpt_gpt4)
 - [UltraChat 200k (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)
 - [AgentInstruct (en)](https://huggingface.co/datasets/THUDM/AgentInstruct)
 - [LMSYS Chat 1M (en)](https://huggingface.co/datasets/lmsys/lmsys-chat-1m)
 - [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)
-- [Glaive Function Calling V2 (en)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
 - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)
+- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
+- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
+- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [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)
@@ -246,13 +274,13 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 
 <details><summary>Preference datasets</summary>
 
+- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
+- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
-- [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
-- [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
-- [Orca DPO (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
-- [DPO mix (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
 - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
+- [KTO mixed (en)](https://huggingface.co/datasets/argilla/kto-mix-15k)
 
 </details>
 
@@ -267,59 +295,57 @@ huggingface-cli login
 
 | Mandatory    | Minimum | Recommend |
 | ------------ | ------- | --------- |
-| python       | 3.8     | 3.10      |
-| torch        | 1.13.1  | 2.2.0     |
-| transformers | 4.37.2  | 4.39.3    |
-| datasets     | 2.14.3  | 2.18.0    |
-| accelerate   | 0.27.2  | 0.28.0    |
-| peft         | 0.9.0   | 0.10.0    |
-| trl          | 0.8.1   | 0.8.1     |
+| python       | 3.8     | 3.11      |
+| torch        | 1.13.1  | 2.3.0     |
+| transformers | 4.41.2  | 4.41.2    |
+| datasets     | 2.16.0  | 2.19.2    |
+| accelerate   | 0.30.1  | 0.30.1    |
+| peft         | 0.11.1  | 0.11.1    |
+| trl          | 0.8.6   | 0.9.4     |
 
 | Optional     | Minimum | Recommend |
 | ------------ | ------- | --------- |
 | CUDA         | 11.6    | 12.2      |
 | deepspeed    | 0.10.0  | 0.14.0    |
-| bitsandbytes | 0.39.0  | 0.43.0    |
-| flash-attn   | 2.3.0   | 2.5.6     |
+| bitsandbytes | 0.39.0  | 0.43.1    |
+| vllm         | 0.4.3   | 0.4.3     |
+| flash-attn   | 2.3.0   | 2.5.9     |
 
 ### Hardware Requirement
 
 \* *estimated*
 
-| Method            | Bits |   7B  |  13B  |  30B  |   70B  |  8x7B |  8x22B |
-| ----------------- | ---- | ----- | ----- | ----- | ------ | ----- | ------ |
-| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 900GB | 2400GB |
-| Full              |  16  |  60GB | 120GB | 300GB |  600GB | 400GB | 1200GB |
-| Freeze            |  16  |  20GB |  40GB |  80GB |  200GB | 160GB |  400GB |
-| LoRA/GaLore/BAdam |  16  |  16GB |  32GB |  64GB |  160GB | 120GB |  320GB |
-| QLoRA             |   8  |  10GB |  20GB |  40GB |   80GB |  60GB |  160GB |
-| QLoRA             |   4  |   6GB |  12GB |  24GB |   48GB |  30GB |   96GB |
-| QLoRA             |   2  |   4GB |   8GB |  16GB |   24GB |  18GB |   48GB |
+| Method            | Bits |   7B  |  13B  |  30B  |   70B  |  110B  |  8x7B |  8x22B |
+| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
+| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |
+| Full              |  16  |  60GB | 120GB | 300GB |  600GB |  900GB | 400GB | 1200GB |
+| Freeze            |  16  |  20GB |  40GB |  80GB |  200GB |  360GB | 160GB |  400GB |
+| LoRA/GaLore/BAdam |  16  |  16GB |  32GB |  64GB |  160GB |  240GB | 120GB |  320GB |
+| QLoRA             |   8  |  10GB |  20GB |  40GB |   80GB |  140GB |  60GB |  160GB |
+| QLoRA             |   4  |   6GB |  12GB |  24GB |   48GB |   72GB |  30GB |   96GB |
+| QLoRA             |   2  |   4GB |   8GB |  16GB |   24GB |   48GB |  18GB |   48GB |
 
 ## Getting Started
 
-### Data Preparation
+### Installation
 
-Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.
-
-> [!NOTE]
-> Please update `data/dataset_info.json` to use your custom dataset.
-
-### Dependence Installation
+> [!IMPORTANT]
+> Installation is mandatory.
 
 ```bash
-git clone https://github.com/hiyouga/LLaMA-Factory.git
-conda create -n llama_factory python=3.10
-conda activate llama_factory
+git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e .[metrics]
+pip install -e '.[torch,metrics]'
 ```
 
-Extra dependencies available: deepspeed, metrics, unsloth, galore, badam, vllm, bitsandbytes, gptq, awq, aqlm, qwen, modelscope, quality
+Extra dependencies available: torch, torch_npu, metrics, deepspeed, bitsandbytes, vllm, galore, badam, gptq, awq, aqlm, qwen, modelscope, quality
+
+> [!TIP]
+> Use `pip install --no-deps -e .` to resolve package conflicts.
 
 <details><summary>For Windows users</summary>
 
-If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you will be required to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.2, please select the appropriate [release version](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels) based on your CUDA version.
+If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you need to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.2, please select the appropriate [release version](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels) based on your CUDA version.
 
 ```bash
 pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.2.post2-py3-none-win_amd64.whl
@@ -329,19 +355,76 @@ To enable FlashAttention-2 on the Windows platform, you need to install the prec
 
 </details>
 
-### LLaMA Board GUI
+<details><summary>For Ascend NPU users</summary>
 
-> [!IMPORTANT]
-> LLaMA Board GUI only supports training on a single GPU, please use [CLI](#command-line-interface) for distributed training.
+Join [NPU user group](assets/wechat_npu.jpg).
+
+To install LLaMA Factory on Ascend NPU devices, please specify extra dependencies: `pip install -e '.[torch-npu,metrics]'`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:
+
+```bash
+# replace the url according to your CANN version and devices
+# install CANN Toolkit
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run
+bash Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run --install
+
+# install CANN Kernels
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run
+bash Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run --install
+
+# set env variables
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+```
+
+| Requirement  | Minimum | Recommend   |
+| ------------ | ------- | ----------- |
+| CANN         | 8.0.RC1 | 8.0.RC1     |
+| torch        | 2.1.0   | 2.1.0       |
+| torch-npu    | 2.1.0   | 2.1.0.post3 |
+| deepspeed    | 0.13.2  | 0.13.2      |
+
+Docker image:
+
+- 32GB: [Download page](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html)
+- 64GB: [Download page](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)
+
+Remember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.
+
+If you cannot infer model on NPU devices, try setting `do_sample: false` in the configurations.
+
+</details>
+
+### Data Preparation
+
+Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.
+
+> [!NOTE]
+> Please update `data/dataset_info.json` to use your custom dataset.
+
+### Quickstart
+
+Use the following 3 commands to run LoRA **fine-tuning**, **inference** and **merging** of the Llama3-8B-Instruct model, respectively.
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+```
+
+See [examples/README.md](examples/README.md) for advanced usage (including distributed training).
+
+> [!TIP]
+> Use `llamafactory-cli help` to show help information.
+
+### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio))
 
 #### Use local environment
 
 ```bash
-export CUDA_VISIBLE_DEVICES=0 # `set CUDA_VISIBLE_DEVICES=0` for Windows
-export GRADIO_SERVER_PORT=7860 # `set GRADIO_SERVER_PORT=7860` for Windows
-python src/train_web.py # or python -m llmtuner.webui.interface
+CUDA_VISIBLE_DEVICES=0 GRADIO_SHARE=1 llamafactory-cli webui
 ```
 
+</details>
+
 #### Use Docker
 
 ```bash
@@ -350,7 +433,6 @@ docker run --gpus=all \
     -v ./hf_cache:/root/.cache/huggingface/ \
     -v ./data:/app/data \
     -v ./output:/app/output \
-    -e CUDA_VISIBLE_DEVICES=0 \
     -p 7860:7860 \
     --shm-size 16G \
     --name llama_factory \
@@ -371,23 +453,16 @@ docker compose -f ./docker-compose.yml up -d
 
 </details>
 
-### Command Line Interface
-
-See [examples/README.md](examples/README.md) for usage.
-
-Use `python src/train_bash.py -h` to display arguments description.
-
 ### Deploy with OpenAI-style API and vLLM
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 python src/api_demo.py \
-    --model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
-    --template mistral \
-    --infer_backend vllm \
-    --vllm_enforce_eager
+CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
 ```
 
-### Use ModelScope Hub
+> [!TIP]
+> Visit https://platform.openai.com/docs/api-reference/chat/create for API document.
+
+### Download from ModelScope Hub
 
 If you have trouble with downloading models and datasets from Hugging Face, you can use ModelScope.
 
@@ -395,7 +470,18 @@ If you have trouble with downloading models and datasets from Hugging Face, you
 export USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows
 ```
 
-Train the model by specifying a model ID of the ModelScope Hub as the `--model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `modelscope/Llama-2-7b-ms`.
+Train the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`.
+
+### Use W&B Logger
+
+To use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments.
+
+```yaml
+report_to: wandb
+run_name: test_run # optional
+```
+
+Set `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account.
 
 ## Projects using LLaMA Factory
 
@@ -424,6 +510,7 @@ If you have a project that should be incorporated, please contact via email or c
 1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333)
 1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419)
 1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228)
+1. Wu et al. Large Language Models are Parallel Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2403.09073)
 1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541)
 1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246)
 1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2403.16008)
@@ -431,12 +518,21 @@ If you have a project that should be incorporated, please contact via email or c
 1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604)
 1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827)
 1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167)
+1. Ma et al. Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation. 2024. [[arxiv]](https://arxiv.org/abs/2404.04316)
 1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084)
+1. Shang et al. How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.09836)
+1. Huang et al. LLMTune: Accelerate Database Knob Tuning with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.11581)
+1. Deng et al. Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction. 2024. [[arxiv]](https://arxiv.org/abs/2404.14215)
+1. Acikgoz et al. Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2404.16621)
+1. Zhang et al. Small Language Models Need Strong Verifiers to Self-Correct Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2404.17140)
+1. Zhou et al. FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2404.18585)
 1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: A large language model for Astronomy, based on ChatGLM2-6B and Qwen-14B.
 1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: A large language model specialized in Chinese legal domain, based on Baichuan-13B, is capable of retrieving and reasoning on legal knowledge.
-1. **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B.
+1. **[Sunsimiao](https://github.com/X-D-Lab/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B.
 1. **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: A series of large language models for Chinese medical domain, based on LLaMA2-7B and Baichuan-13B.
 1. **[MachineMindset](https://github.com/PKU-YuanGroup/Machine-Mindset/)**: A series of MBTI Personality large language models, capable of giving any LLM 16 different personality types based on different datasets and training methods.
+1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**: A large language model specialized in generate metadata for stable diffusion. [[🤗Demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)
+1. **[Chinese-LLaVA-Med](https://github.com/BUAADreamer/Chinese-LLaVA-Med)**: A multimodal large language model specialized in Chinese medical domain, based on LLaVA-1.5-7B.
 
 </details>
 
@@ -444,7 +540,7 @@ If you have a project that should be incorporated, please contact via email or c
 
 This repository is licensed under the [Apache-2.0 License](LICENSE).
 
-Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command-R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
+Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command-R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
 
 ## Citation
 

README_zh.md

@@ -3,15 +3,17 @@
 [![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)
 [![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)
 [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)
-[![PyPI](https://img.shields.io/pypi/v/llmtuner)](https://pypi.org/project/llmtuner/)
-[![Downloads](https://static.pepy.tech/badge/llmtuner)](https://pypi.org/project/llmtuner/)
-[![Citation](https://img.shields.io/badge/citation-34-green)](#使用了-llama-factory-的项目)
+[![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
+[![Citation](https://img.shields.io/badge/citation-44-green)](#使用了-llama-factory-的项目)
 [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
 [![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)
 [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing)
+[![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)
 [![Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
 [![Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)
+
+[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)
 
 👋 加入我们的[微信群](assets/wechat.jpg)。
 
@@ -23,7 +25,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 选择你的打开方式：
 
-- **Colab**：https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing
+- **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
+- **PAI-DSW**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
 - **本地机器**：请见[如何使用](#如何使用)
 
 ## 目录
@@ -43,8 +46,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 ## 项目特色
 
-- **多种模型**：LLaMA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
-- **集成方法**：（增量）预训练、指令监督微调、奖励模型训练、PPO 训练、DPO 训练和 ORPO 训练。
+- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
+- **集成方法**：（增量）预训练、（多模态）指令监督微调、奖励模型训练、PPO 训练、DPO 训练、KTO 训练、ORPO 训练等等。
 - **多种精度**：32 比特全参数微调、16 比特冻结微调、16 比特 LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8 的 2/4/8 比特 QLoRA 微调。
 - **先进算法**：GaLore、BAdam、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ 和 Agent 微调。
 - **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。
@@ -68,55 +71,69 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 ## 更新日志
 
-[24/04/21] 我们基于 [AstraMindAI 的仓库](https://github.com/astramind-ai/Mixture-of-depths)支持了 **[混合深度训练](https://arxiv.org/abs/2404.02258)**。详细用法请参照 `examples/extras/mod`。
+[24/06/07] 我们支持了 **[Qwen-2](https://qwenlm.github.io/blog/qwen2/)** 系列模型的微调。
 
-[24/04/19] 我们支持了 **Meta Llama 3** 系列模型。
+[24/06/05] 我们支持了 **[GLM-4-9B/GLM-4-9B-Chat](https://github.com/THUDM/GLM-4)** 模型的微调。
 
-[24/04/16] 我们支持了 **[BAdam](https://arxiv.org/abs/2404.02827)**。详细用法请参照 `examples/extras/badam`。
-
-[24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 Llama-2-7B-56k）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
+[24/05/26] 我们支持了 **[SimPO](https://arxiv.org/abs/2405.14734)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
 
 <details><summary>展开日志</summary>
 
-[24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 `examples/lora_single_gpu`。
+[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `gemma` 模板进行微调使其获得对话能力。
+
+[24/05/18] 我们支持了 **[KTO](https://arxiv.org/abs/2402.01306)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/05/14] 我们支持了昇腾 NPU 设备的训练和推理。详情请查阅[安装](#安装-llama-factory)部分。
+
+[24/04/26] 我们支持了多模态模型 **LLaVA-1.5** 的微调。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/22] 我们提供了在免费 T4 GPU 上微调 Llama-3 模型的 **[Colab 笔记本](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing)**。Hugging Face 社区公开了两个利用 LLaMA Factory 微调的 Llama-3 模型，详情请见 [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) 和 [Llama3-Chinese](https://huggingface.co/zhichen/Llama3-Chinese)。
+
+[24/04/21] 我们基于 [AstraMindAI 的仓库](https://github.com/astramind-ai/Mixture-of-depths)支持了 **[混合深度训练](https://arxiv.org/abs/2404.02258)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/16] 我们支持了 **[BAdam](https://arxiv.org/abs/2404.02827)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 Llama-2-7B-56k）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
+
+[24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 [examples](examples/README_zh.md)。
 
 [24/03/21] 我们的论文 "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" 可在 arXiv 上查看！
 
-[24/03/20] 我们支持了能在 2x24GB GPU 上微调 70B 模型的 **FSDP+QLoRA**。详细用法请参照 `examples/extras/fsdp_qlora`。
+[24/03/20] 我们支持了能在 2x24GB GPU 上微调 70B 模型的 **FSDP+QLoRA**。详细用法请参照 [examples](examples/README_zh.md)。
 
-[24/03/13] 我们支持了 **[LoRA+](https://arxiv.org/abs/2402.12354)**。详细用法请参照 `examples/extras/loraplus`。
+[24/03/13] 我们支持了 **[LoRA+](https://arxiv.org/abs/2402.12354)**。详细用法请参照 [examples](examples/README_zh.md)。
 
-[24/03/07] 我们支持了梯度低秩投影（**[GaLore](https://arxiv.org/abs/2403.03507)**）算法。详细用法请参照 `examples/extras/galore`。
+[24/03/07] 我们支持了梯度低秩投影（**[GaLore](https://arxiv.org/abs/2403.03507)**）算法。详细用法请参照 [examples](examples/README_zh.md)。
 
-[24/03/07] 我们集成了 **[vLLM](https://github.com/vllm-project/vllm)** 以实现极速并发推理。请使用 `--infer_backend vllm` 来获得 **270%** 的推理速度。（尚不支持 LoRA，请先合并权重。）
+[24/03/07] 我们集成了 **[vLLM](https://github.com/vllm-project/vllm)** 以实现极速并发推理。请使用 `infer_backend: vllm` 来获得 **270%** 的推理速度。
 
-[24/02/28] 我们支持了 **[DoRA](https://arxiv.org/abs/2402.09353)** 微调。请使用 `--use_dora` 参数进行 DoRA 微调。
+[24/02/28] 我们支持了 **[DoRA](https://arxiv.org/abs/2402.09353)** 微调。请使用 `use_dora: true` 参数进行 DoRA 微调。
 
-[24/02/15] 我们支持了 [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro) 提出的**块扩展**方法。详细用法请参照 `examples/extras/llama_pro`。
+[24/02/15] 我们支持了 [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro) 提出的**块扩展**方法。详细用法请参照 [examples](examples/README_zh.md)。
 
 [24/02/05] Qwen1.5（Qwen2 测试版）系列模型已在 LLaMA-Factory 中实现微调支持。详情请查阅该[博客页面](https://qwenlm.github.io/zh/blog/qwen1.5/)。
 
-[24/01/18] 我们针对绝大多数模型实现了 **Agent 微调**，微调时指定 `--dataset glaive_toolcall` 即可使模型获得工具调用能力。
+[24/01/18] 我们针对绝大多数模型实现了 **Agent 微调**，微调时指定 `dataset: glaive_toolcall_zh` 即可使模型获得工具调用能力。
 
-[23/12/23] 我们针对 LLaMA, Mistral 和 Yi 模型支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的 LoRA 训练加速。请使用 `--use_unsloth` 参数启用 unsloth 优化。该方法可提供 **170%** 的训练速度，详情请查阅[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
+[23/12/23] 我们针对 LLaMA, Mistral 和 Yi 模型支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的 LoRA 训练加速。请使用 `use_unsloth: true` 参数启用 unsloth 优化。该方法可提供 **170%** 的训练速度，详情请查阅[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
 
 [23/12/12] 我们支持了微调最新的混合专家模型 **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)**。硬件需求请查阅[此处](#硬件依赖)。
 
-[23/12/01] 我们支持了从 **[魔搭社区](https://modelscope.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#使用魔搭社区可跳过)。
+[23/12/01] 我们支持了从 **[魔搭社区](https://modelscope.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔搭社区下载)。
 
-[23/10/21] 我们支持了 **[NEFTune](https://arxiv.org/abs/2310.05914)** 训练技巧。请使用 `--neftune_noise_alpha` 参数启用 NEFTune，例如 `--neftune_noise_alpha 5`。
+[23/10/21] 我们支持了 **[NEFTune](https://arxiv.org/abs/2310.05914)** 训练技巧。请使用 `neftune_noise_alpha: 5` 参数启用 NEFTune。
 
-[23/09/27] 我们针对 LLaMA 模型支持了 [LongLoRA](https://github.com/dvlab-research/LongLoRA) 提出的 **$S^2$-Attn**。请使用 `--shift_attn` 参数以启用该功能。
+[23/09/27] 我们针对 LLaMA 模型支持了 [LongLoRA](https://github.com/dvlab-research/LongLoRA) 提出的 **$S^2$-Attn**。请使用 `shift_attn: true` 参数以启用该功能。
 
-[23/09/23] 我们在项目中集成了 MMLU、C-Eval 和 CMMLU 评估集。使用方法请参阅[此示例](#模型评估)。
+[23/09/23] 我们在项目中集成了 MMLU、C-Eval 和 CMMLU 评估集。详细用法请参照 [examples](examples/README_zh.md)。
 
-[23/09/10] 我们支持了 **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**。如果您使用的是 RTX4090、A100 或 H100 GPU，请使用 `--flash_attn` 参数以启用 FlashAttention-2。
+[23/09/10] 我们支持了 **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**。如果您使用的是 RTX4090、A100 或 H100 GPU，请使用 `flash_attn: fa2` 参数以启用 FlashAttention-2。
 
-[23/08/12] 我们支持了 **RoPE 插值**来扩展 LLaMA 模型的上下文长度。请使用 `--rope_scaling linear` 参数训练模型或使用 `--rope_scaling dynamic` 参数评估模型。
+[23/08/12] 我们支持了 **RoPE 插值**来扩展 LLaMA 模型的上下文长度。请使用 `rope_scaling: linear` 参数训练模型或使用 `rope_scaling: dynamic` 参数评估模型。
 
-[23/08/11] 我们支持了指令模型的 **[DPO 训练](https://arxiv.org/abs/2305.18290)**。使用方法请参阅[此示例](#dpo-训练)。
+[23/08/11] 我们支持了指令模型的 **[DPO 训练](https://arxiv.org/abs/2305.18290)**。详细用法请参照 [examples](examples/README_zh.md)。
 
-[23/07/31] 我们支持了**数据流式加载**。请使用 `--streaming` 和 `--max_steps 10000` 参数来流式加载数据集。
+[23/07/31] 我们支持了**数据流式加载**。请使用 `streaming: true` 和 `max_steps: 10000` 参数来流式加载数据集。
 
 [23/07/29] 我们在 Hugging Face 发布了两个 13B 指令微调模型。详细内容请查阅我们的 Hugging Face 项目（[LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)）。
 
@@ -128,44 +145,50 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 [23/06/22] 我们对齐了[示例 API](src/api_demo.py) 与 [OpenAI API](https://platform.openai.com/docs/api-reference/chat) 的格式，您可以将微调模型接入**任意基于 ChatGPT 的应用**中。
 
-[23/06/03] 我们实现了 4 比特的 LoRA 训练（也称 **[QLoRA](https://github.com/artidoro/qlora)**）。请使用 `--quantization_bit 4` 参数进行 4 比特量化微调。
+[23/06/03] 我们实现了 4 比特的 LoRA 训练（也称 **[QLoRA](https://github.com/artidoro/qlora)**）。详细用法请参照 [examples](examples/README_zh.md)。
 
 </details>
 
 ## 模型
 
-| 模型名                                                   | 模型大小                     | 默认模块           | Template  |
-| -------------------------------------------------------- | --------------------------- | ----------------- | --------- |
-| [Baichuan2](https://huggingface.co/baichuan-inc)         | 7B/13B                      | W_pack            | baichuan2 |
-| [BLOOM](https://huggingface.co/bigscience)               | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value   | -         |
-| [BLOOMZ](https://huggingface.co/bigscience)              | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value   | -         |
-| [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                          | query_key_value   | chatglm3  |
-| [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                    | q_proj,v_proj     | cohere    |
-| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B                  | q_proj,v_proj     | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                 | query_key_value   | falcon    |
-| [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                       | q_proj,v_proj     | gemma     |
-| [InternLM2](https://huggingface.co/internlm)             | 7B/20B                      | wqkv              | intern2   |
-| [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B              | q_proj,v_proj     | -         |
-| [LLaMA-2](https://huggingface.co/meta-llama)             | 7B/13B/70B                  | q_proj,v_proj     | llama2    |
-| [LLaMA-3](https://huggingface.co/meta-llama)             | 8B/70B                      | q_proj,v_proj     | llama3    |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B               | q_proj,v_proj     | mistral   |
-| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                       | att_proj          | olmo      |
-| [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                   | q_proj,v_proj     | -         |
-| [Qwen](https://huggingface.co/Qwen)                      | 1.8B/7B/14B/72B             | c_attn            | qwen      |
-| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B | q_proj,v_proj     | qwen      |
-| [StarCoder2](https://huggingface.co/bigcode)             | 3B/7B/15B                   | q_proj,v_proj     | -         |
-| [XVERSE](https://huggingface.co/xverse)                  | 7B/13B/65B                  | q_proj,v_proj     | xverse    |
-| [Yi](https://huggingface.co/01-ai)                       | 6B/9B/34B                   | q_proj,v_proj     | yi        |
-| [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                 | q_proj,v_proj     | yuan      |
+| 模型名                                                   | 模型大小                          | Template  |
+| -------------------------------------------------------- | -------------------------------- | --------- |
+| [Baichuan2](https://huggingface.co/baichuan-inc)         | 7B/13B                           | baichuan2 |
+| [BLOOM](https://huggingface.co/bigscience)               | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
+| [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 (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek  |
+| [Falcon](https://huggingface.co/tiiuae)                  | 7B/11B/40B/180B                  | falcon    |
+| [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | gemma     |
+| [GLM4](https://huggingface.co/THUDM)                     | 9B                               | glm4      |
+| [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | intern2   |
+| [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B                   | -         |
+| [LLaMA-2](https://huggingface.co/meta-llama)             | 7B/13B/70B                       | llama2    |
+| [LLaMA-3](https://huggingface.co/meta-llama)             | 8B/70B                           | llama3    |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)             | 7B/13B                           | vicuna    |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B                    | mistral   |
+| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                            | -         |
+| [PaliGemma](https://huggingface.co/google)               | 3B                               | gemma     |
+| [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                        | -         |
+| [Phi-3](https://huggingface.co/microsoft)                | 4B/7B/14B                        | phi       |
+| [Qwen](https://huggingface.co/Qwen)                      | 1.8B/7B/14B/72B                  | qwen      |
+| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | qwen      |
+| [Qwen2 (MoE)](https://huggingface.co/Qwen)               | 0.5B/1.5B/7B/57B/72B             | qwen      |
+| [StarCoder2](https://huggingface.co/bigcode)             | 3B/7B/15B                        | -         |
+| [XVERSE](https://huggingface.co/xverse)                  | 7B/13B/65B                       | xverse    |
+| [Yi (1/1.5)](https://huggingface.co/01-ai)               | 6B/9B/34B                        | yi        |
+| [Yi-VL](https://huggingface.co/01-ai)                    | 6B/34B                           | yi_vl     |
+| [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                      | yuan      |
 
 > [!NOTE]
-> **默认模块**应作为 `--lora_target` 参数的默认值，可使用 `--lora_target all` 参数指定全部模块。
+> 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
 >
-> 对于所有“基座”（Base）模型，`--template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Chat）模型请务必使用**对应的模板**。
+> 请务必在训练和推理时采用**完全一致**的模板。
 
-项目所支持模型的完整列表请参阅 [constants.py](src/llmtuner/extras/constants.py)。
+项目所支持模型的完整列表请参阅 [constants.py](src/llamafactory/extras/constants.py)。
 
-您也可以在 [template.py](src/llmtuner/data/template.py) 中添加自己的对话模板。
+您也可以在 [template.py](src/llamafactory/data/template.py) 中添加自己的对话模板。
 
 ## 训练方法
 
@@ -176,7 +199,9 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 | 奖励模型训练            | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | PPO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | DPO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| KTO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | ORPO 训练              | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| SimPO 训练             | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 
 ## 数据集
 
@@ -189,6 +214,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
 - [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
 - [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
+- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
+- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
 - [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
 - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
 
@@ -196,12 +223,12 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 <details><summary>指令微调数据集</summary>
 
+- [Identity (en&zh)](data/identity.json)
 - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
-- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
+- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)
 - [Alpaca GPT4 (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
-- [Self Cognition (zh)](data/self_cognition.json)
-- [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
-- [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection)
+- [Glaive Function Calling V2 (en&zh)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
+- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
 - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
 - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
 - [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN)
@@ -210,7 +237,6 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
 - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
 - [UltraChat (en)](https://github.com/thunlp/UltraChat)
-- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
 - [OpenPlatypus (en)](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)
 - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
 - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
@@ -223,15 +249,17 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
 - [deepctrl (en&zh)](https://www.modelscope.cn/datasets/deepctrl/deepctrl-sft-data)
-- [Ad Gen (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
+- [Advertise Generating (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
 - [ShareGPT Hyperfiltered (en)](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k)
 - [ShareGPT4 (en&zh)](https://huggingface.co/datasets/shibing624/sharegpt_gpt4)
 - [UltraChat 200k (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)
 - [AgentInstruct (en)](https://huggingface.co/datasets/THUDM/AgentInstruct)
 - [LMSYS Chat 1M (en)](https://huggingface.co/datasets/lmsys/lmsys-chat-1m)
 - [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)
-- [Glaive Function Calling V2 (en)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
 - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)
+- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
+- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
+- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [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)
@@ -246,13 +274,13 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 
 <details><summary>偏好数据集</summary>
 
+- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
+- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
-- [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
-- [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
-- [Orca DPO (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
-- [DPO mix (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
 - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
+- [KTO mixed (en)](https://huggingface.co/datasets/argilla/kto-mix-15k)
 
 </details>
 
@@ -267,55 +295,53 @@ huggingface-cli login
 
 | 必需项       | 至少     | 推荐      |
 | ------------ | ------- | --------- |
-| python       | 3.8     | 3.10      |
-| torch        | 1.13.1  | 2.2.0     |
-| transformers | 4.37.2  | 4.39.3    |
-| datasets     | 2.14.3  | 2.18.0    |
-| accelerate   | 0.27.2  | 0.28.0    |
-| peft         | 0.9.0   | 0.10.0    |
-| trl          | 0.8.1   | 0.8.1     |
+| python       | 3.8     | 3.11      |
+| torch        | 1.13.1  | 2.3.0     |
+| transformers | 4.41.2  | 4.41.2    |
+| datasets     | 2.16.0  | 2.19.2    |
+| accelerate   | 0.30.1  | 0.30.1    |
+| peft         | 0.11.1  | 0.11.1    |
+| trl          | 0.8.6   | 0.9.4     |
 
 | 可选项       | 至少     | 推荐      |
 | ------------ | ------- | --------- |
 | CUDA         | 11.6    | 12.2      |
 | deepspeed    | 0.10.0  | 0.14.0    |
-| bitsandbytes | 0.39.0  | 0.43.0    |
-| flash-attn   | 2.3.0   | 2.5.6     |
+| bitsandbytes | 0.39.0  | 0.43.1    |
+| vllm         | 0.4.3   | 0.4.3     |
+| flash-attn   | 2.3.0   | 2.5.9     |
 
 ### 硬件依赖
 
 \* *估算值*
 
-| 方法              | 精度 |   7B  |  13B  |  30B  |   70B  |  8x7B |  8x22B |
-| ----------------- | ---- | ----- | ----- | ----- | ------ | ----- | ------ |
-| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 900GB | 2400GB |
-| Full              |  16  |  60GB | 120GB | 300GB |  600GB | 400GB | 1200GB |
-| Freeze            |  16  |  20GB |  40GB |  80GB |  200GB | 160GB |  400GB |
-| LoRA/GaLore/BAdam |  16  |  16GB |  32GB |  64GB |  160GB | 120GB |  320GB |
-| QLoRA             |   8  |  10GB |  20GB |  40GB |   80GB |  60GB |  160GB |
-| QLoRA             |   4  |   6GB |  12GB |  24GB |   48GB |  30GB |   96GB |
-| QLoRA             |   2  |   4GB |   8GB |  16GB |   24GB |  18GB |   48GB |
+| 方法               | 精度 |   7B  |  13B  |  30B  |   70B  |  110B  |  8x7B |  8x22B |
+| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
+| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |
+| Full              |  16  |  60GB | 120GB | 300GB |  600GB |  900GB | 400GB | 1200GB |
+| Freeze            |  16  |  20GB |  40GB |  80GB |  200GB |  360GB | 160GB |  400GB |
+| LoRA/GaLore/BAdam |  16  |  16GB |  32GB |  64GB |  160GB |  240GB | 120GB |  320GB |
+| QLoRA             |   8  |  10GB |  20GB |  40GB |   80GB |  140GB |  60GB |  160GB |
+| QLoRA             |   4  |   6GB |  12GB |  24GB |   48GB |   72GB |  30GB |   96GB |
+| QLoRA             |   2  |   4GB |   8GB |  16GB |   24GB |   48GB |  18GB |   48GB |
 
 ## 如何使用
 
-### 数据准备
+### 安装 LLaMA Factory
 
-关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope 上的数据集或加载本地数据集。
-
-> [!NOTE]
-> 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
-
-### 安装依赖
+> [!IMPORTANT]
+> 此步骤为必需。
 
 ```bash
-git clone https://github.com/hiyouga/LLaMA-Factory.git
-conda create -n llama_factory python=3.10
-conda activate llama_factory
+git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
 cd LLaMA-Factory
-pip install -e .[metrics]
+pip install -e '.[torch,metrics]'
 ```
 
-可选的额外依赖项：deepspeed、metrics、unsloth、galore、badam、vllm、bitsandbytes、gptq、awq、aqlm、qwen、modelscope、quality
+可选的额外依赖项：torch、torch_npu、metrics、deepspeed、bitsandbytes、vllm、galore、badam、gptq、awq、aqlm、qwen、modelscope、quality
+
+> [!TIP]
+> 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
 
 <details><summary>Windows 用户指南</summary>
 
@@ -329,17 +355,72 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl
 
 </details>
 
-### LLaMA Board 可视化界面
+<details><summary>昇腾 NPU 用户指南</summary>
 
-> [!IMPORTANT]
-> LLaMA Board 可视化界面目前仅支持单 GPU 训练，请使用[命令行接口](#命令行接口)来进行分布式训练。
+加入 [NPU 用户群](assets/wechat_npu.jpg)。
+
+在昇腾 NPU 设备上安装 LLaMA Factory 时，需要指定额外依赖项，使用 `pip install -e '.[torch-npu,metrics]'` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit and 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
+# 安装 CANN Toolkit
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run
+bash Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run --install
+
+# 安装 CANN Kernels
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run
+bash Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run --install
+
+# 设置环境变量
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+```
+
+| 依赖项       | 至少     | 推荐        |
+| ------------ | ------- | ----------- |
+| CANN         | 8.0.RC1 | 8.0.RC1     |
+| torch        | 2.1.0   | 2.1.0       |
+| torch-npu    | 2.1.0   | 2.1.0.post3 |
+| deepspeed    | 0.13.2  | 0.13.2      |
+
+Docker 镜像：
+
+- 32GB：[下载地址](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html)
+- 64GB：[下载地址](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)
+
+请使用 `ASCEND_RT_VISIBLE_DEVICES` 而非 `CUDA_VISIBLE_DEVICES` 来指定运算设备。
+
+如果遇到无法正常推理的情况，请尝试设置 `do_sample: false`。
+
+</details>
+
+### 数据准备
+
+关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope 上的数据集或加载本地数据集。
+
+> [!NOTE]
+> 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
+
+### 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**。
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+```
+
+高级用法请参考 [examples/README_zh.md](examples/README_zh.md)（包括多 GPU 微调）。
+
+> [!TIP]
+> 使用 `llamafactory-cli help` 显示帮助信息。
+
+### LLaMA Board 可视化微调（由 [Gradio](https://github.com/gradio-app/gradio) 驱动）
 
 #### 使用本地环境
 
 ```bash
-export CUDA_VISIBLE_DEVICES=0 # Windows 使用 `set CUDA_VISIBLE_DEVICES=0`
-export GRADIO_SERVER_PORT=7860 # Windows 使用 `set GRADIO_SERVER_PORT=7860`
-python src/train_web.py # 或 python -m llmtuner.webui.interface
+CUDA_VISIBLE_DEVICES=0 GRADIO_SHARE=1 llamafactory-cli webui
 ```
 
 #### 使用 Docker
@@ -350,7 +431,6 @@ docker run --gpus=all \
     -v ./hf_cache:/root/.cache/huggingface/ \
     -v ./data:/app/data \
     -v ./output:/app/output \
-    -e CUDA_VISIBLE_DEVICES=0 \
     -p 7860:7860 \
     --shm-size 16G \
     --name llama_factory \
@@ -371,23 +451,16 @@ docker compose -f ./docker-compose.yml up -d
 
 </details>
 
-### 命令行接口
-
-使用方法请参考 [examples/README_zh.md](examples/README_zh.md)。
-
-使用 `python src/train_bash.py -h` 查看参数文档。
-
-### 使用 OpenAI 风格 API 和 vLLM 部署
+### 利用 vLLM 部署 OpenAI API
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 python src/api_demo.py \
-    --model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
-    --template mistral \
-    --infer_backend vllm \
-    --vllm_enforce_eager
+CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
 ```
 
-### 使用魔搭社区
+> [!TIP]
+> API 文档请查阅 https://platform.openai.com/docs/api-reference/chat/create。
+
+### 从魔搭社区下载
 
 如果您在 Hugging Face 模型和数据集的下载中遇到了问题，可以通过下述方法使用魔搭社区。
 
@@ -395,7 +468,18 @@ CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 python src/api_demo.py \
 export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 ```
 
-将 `--model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔搭社区](https://modelscope.cn/models)查看所有可用的模型，例如 `modelscope/Llama-2-7b-ms`。
+将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔搭社区](https://modelscope.cn/models)查看所有可用的模型，例如 `LLM-Research/Meta-Llama-3-8B-Instruct`。
+
+### 使用 W&B 面板
+
+若要使用 [Weights & Biases](https://wandb.ai) 记录实验数据，请添加下面的参数。
+
+```yaml
+report_to: wandb
+run_name: test_run # 可选
+```
+
+在启动训练任务时，将 `WANDB_API_KEY` 设置为[密钥](https://wandb.ai/authorize)来登录 W&B 账户。
 
 ## 使用了 LLaMA Factory 的项目
 
@@ -424,6 +508,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333)
 1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419)
 1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228)
+1. Wu et al. Large Language Models are Parallel Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2403.09073)
 1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541)
 1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246)
 1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2403.16008)
@@ -431,12 +516,21 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604)
 1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827)
 1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167)
+1. Ma et al. Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation. 2024. [[arxiv]](https://arxiv.org/abs/2404.04316)
 1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084)
+1. Shang et al. How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.09836)
+1. Huang et al. LLMTune: Accelerate Database Knob Tuning with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.11581)
+1. Deng et al. Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction. 2024. [[arxiv]](https://arxiv.org/abs/2404.14215)
+1. Acikgoz et al. Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2404.16621)
+1. Zhang et al. Small Language Models Need Strong Verifiers to Self-Correct Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2404.17140)
+1. Zhou et al. FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2404.18585)
 1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: 天文大模型 StarWhisper，基于 ChatGLM2-6B 和 Qwen-14B 在天文数据上微调而得。
 1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: 中文法律领域大模型 DISC-LawLLM，基于 Baichuan-13B 微调而得，具有法律推理和知识检索能力。
-1. **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。
+1. **[Sunsimiao](https://github.com/X-D-Lab/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。
 1. **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: 医疗大模型项目 CareGPT，基于 LLaMA2-7B 和 Baichuan-13B 在中文医疗数据上微调而得。
 1. **[MachineMindset](https://github.com/PKU-YuanGroup/Machine-Mindset/)**：MBTI性格大模型项目，根据数据集与训练方式让任意 LLM 拥有 16 个不同的性格类型。
+1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**：一个用于生成 Stable Diffusion 提示词的大型语言模型。[[🤗Demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)
+1. **[Chinese-LLaVA-Med](https://github.com/BUAADreamer/Chinese-LLaVA-Med)**：中文多模态医学大模型，基于 LLaVA-1.5-7B 在中文多模态医疗数据上微调而得。
 
 </details>
 
@@ -444,7 +538,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 
 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。
 
-使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command-R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
+使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command-R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
 
 ## 引用
 

data/README.md

@@ -1,16 +1,18 @@
-If you are using a custom dataset, please provide your dataset definition in the following format in `dataset_info.json`.
+The [dataset_info.json](dataset_info.json) contains all available datasets. If you are using a custom dataset, please **make sure** to add a *dataset description* in `dataset_info.json` and specify `dataset: dataset_name` before training to use it.
+
+Currently we support datasets in **alpaca** and **sharegpt** format.
 
 ```json
 "dataset_name": {
   "hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore script_url and file_name)",
-  "ms_hub_url": "the name of the dataset repository on the ModelScope hub. (if specified, ignore script_url and file_name)",
+  "ms_hub_url": "the name of the dataset repository on the Model Scope hub. (if specified, ignore script_url and file_name)",
   "script_url": "the name of the directory containing a dataset loading script. (if specified, ignore file_name)",
-  "file_name": "the name of the dataset file in this directory. (required if above are not specified)",
-  "file_sha1": "the SHA-1 hash value of the dataset file. (optional, does not affect training)",
+  "file_name": "the name of the dataset folder or dataset file in this directory. (required if above are not specified)",
+  "formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
+  "ranking": "whether the dataset is a preference dataset or not. (default: False)",
   "subset": "the name of the subset. (optional, default: None)",
   "folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
-  "ranking": "whether the dataset is a preference dataset or not. (default: false)",
-  "formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
+  "num_samples": "the number of samples in the dataset used for training. (optional, default: None)",
   "columns (optional)": {
     "prompt": "the column name in the dataset containing the prompts. (default: instruction)",
     "query": "the column name in the dataset containing the queries. (default: input)",
@@ -18,7 +20,11 @@ If you are using a custom dataset, please provide your dataset definition in the
     "history": "the column name in the dataset containing the histories. (default: None)",
     "messages": "the column name in the dataset containing the messages. (default: conversations)",
     "system": "the column name in the dataset containing the system prompts. (default: None)",
-    "tools": "the column name in the dataset containing the tool description. (default: None)"
+    "tools": "the column name in the dataset containing the tool description. (default: None)",
+    "images": "the column name in the dataset containing the image inputs. (default: None)",
+    "chosen": "the column name in the dataset containing the chosen answers. (default: None)",
+    "rejected": "the column name in the dataset containing the rejected answers. (default: None)",
+    "kto_tag": "the column name in the dataset containing the kto tags. (default: None)"
   },
   "tags (optional, used for the sharegpt format)": {
     "role_tag": "the key in the message represents the identity. (default: from)",
@@ -32,31 +38,38 @@ If you are using a custom dataset, please provide your dataset definition in the
 }
 ```
 
-Given above, you can use the custom dataset via specifying `--dataset dataset_name`.
+## Alpaca Format
 
-----
+### Supervised Fine-Tuning Dataset
 
-Currently we support dataset in **alpaca** or **sharegpt** format, the dataset in alpaca format should follow the below format:
+* [Example dataset](alpaca_en_demo.json)
+
+In supervised fine-tuning, the `instruction` column will be concatenated with the `input` column and used as the human prompt, then the human prompt would be `instruction\ninput`. The `output` column represents the model response.
+
+The `system` column will be used as the system prompt if specified.
+
+The `history` column is a list consisting of string tuples representing prompt-response pairs in the history messages. Note that the responses in the history **will also be learned by the model** in supervised fine-tuning.
 
 ```json
 [
   {
-    "instruction": "user instruction (required)",
-    "input": "user input (optional)",
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
     "output": "model response (required)",
     "system": "system prompt (optional)",
     "history": [
-      ["user instruction in the first round (optional)", "model response in the first round (optional)"],
-      ["user instruction in the second round (optional)", "model response in the second round (optional)"]
+      ["human instruction in the first round (optional)", "model response in the first round (optional)"],
+      ["human instruction in the second round (optional)", "model response in the second round (optional)"]
     ]
   }
 ]
 ```
 
-Regarding the above dataset, the `columns` in `dataset_info.json` should be:
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
 
 ```json
 "dataset_name": {
+  "file_name": "data.json",
   "columns": {
     "prompt": "instruction",
     "query": "input",
@@ -67,30 +80,135 @@ Regarding the above dataset, the `columns` in `dataset_info.json` should be:
 }
 ```
 
-The `query` column will be concatenated with the `prompt` column and used as the user prompt, then the user prompt would be `prompt\nquery`. The `response` column represents the model response.
+### Pre-training Dataset
 
-The `system` column will be used as the system prompt. The `history` column is a list consisting string tuples representing prompt-response pairs in the history. Note that the responses in the history **will also be used for training**.
+- [Example dataset](c4_demo.json)
 
-For the pre-training datasets, only the `prompt` column will be used for training.
-
-For the preference datasets, the `response` column should be a string list whose length is 2, with the preferred answers appearing first, for example:
+In pre-training, only the `text` column will be used for model learning.
 
 ```json
-{
-  "instruction": "user instruction",
-  "input": "user input",
-  "output": [
-    "chosen answer",
-    "rejected answer"
-  ]
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
 }
 ```
 
-Remember to set `"ranking": true` for the preference datasets.
+### Preference Dataset
 
-----
+Preference datasets are used for reward modeling, DPO training and ORPO training.
 
-The dataset in sharegpt format should follow the below format:
+It requires a better response in `chosen` column and a worse response in `rejected` column.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "chosen": "chosen answer (required)",
+    "rejected": "rejected answer (required)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### KTO Dataset
+
+- [Example dataset](kto_en_demo.json)
+
+KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "output": "model response (required)",
+    "kto_tag": "human feedback [true/false] (required)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### Multimodal Dataset
+
+- [Example dataset](mllm_demo.json)
+
+Multimodal datasets require a `images` column containing the paths to the input images. Currently we only support one image.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "output": "model response (required)",
+    "images": [
+      "image path (required)"
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "images": "images"
+  }
+}
+```
+
+## Sharegpt Format
+
+### Supervised Fine-Tuning Dataset
+
+- [Example dataset](glaive_toolcall_en_demo.json)
+
+Compared to the alpaca format, the sharegpt format allows the datasets have **more roles**, such as human, gpt, observation and function. They are presented in a list of objects in the `conversations` column.
+
+Note that the human and observation should appear in odd positions, while gpt and function should appear in even positions.
 
 ```json
 [
@@ -98,7 +216,15 @@ The dataset in sharegpt format should follow the below format:
     "conversations": [
       {
         "from": "human",
-        "value": "user instruction"
+        "value": "human instruction"
+      },
+      {
+        "from": "function_call",
+        "value": "tool arguments"
+      },
+      {
+        "from": "observation",
+        "value": "tool result"
       },
       {
         "from": "gpt",
@@ -111,24 +237,114 @@ The dataset in sharegpt format should follow the below format:
 ]
 ```
 
-Regarding the above dataset, the `columns` in `dataset_info.json` should be:
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
 
 ```json
 "dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
   "columns": {
     "messages": "conversations",
     "system": "system",
     "tools": "tools"
-  },
-  "tags": {
-    "role_tag": "from",
-    "content_tag": "value",
-    "user_tag": "human",
-    "assistant_tag": "gpt"
   }
 }
 ```
 
-where the `messages` column should be a list following the `u/a/u/a/u/a` order.
+### Preference Dataset
 
-Pre-training datasets and preference datasets are incompatible with the sharegpt format yet.
+- [Example dataset](dpo_en_demo.json)
+
+Preference datasets in sharegpt format also require a better message in `chosen` column and a worse message in `rejected` column.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      },
+      {
+        "from": "human",
+        "value": "human instruction"
+      }
+    ],
+    "chosen": {
+      "from": "gpt",
+      "value": "chosen answer (required)"
+    },
+    "rejected": {
+      "from": "gpt",
+      "value": "rejected answer (required)"
+    }
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "ranking": true,
+  "columns": {
+    "messages": "conversations",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### OpenAI Format
+
+The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "system prompt (optional)"
+      },
+      {
+        "role": "user",
+        "content": "human instruction"
+      },
+      {
+        "role": "assistant",
+        "content": "model response"
+      }
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "messages"
+  },
+  "tags": {
+    "role_tag": "role",
+    "content_tag": "content",
+    "user_tag": "user",
+    "assistant_tag": "assistant",
+    "system_tag": "system"
+  }
+}
+```
+
+The KTO datasets and multimodal datasets in sharegpt format are similar to the alpaca format.
+
+Pre-training datasets are **incompatible** with the sharegpt format.

data/README_zh.md

@@ -1,16 +1,18 @@
-如果您使用自定义数据集，请务必在 `dataset_info.json` 文件中按照以下格式提供数据集定义。
+[dataset_info.json](dataset_info.json) 包含了所有可用的数据集。如果您希望使用自定义数据集，请**务必**在 `dataset_info.json` 文件中添加*数据集描述*，并通过修改 `dataset: 数据集名称` 配置来使用数据集。
+
+目前我们支持 **alpaca** 格式和 **sharegpt** 格式的数据集。
 
 ```json
 "数据集名称": {
   "hf_hub_url": "Hugging Face 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
   "ms_hub_url": "ModelScope 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
   "script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略 file_name）",
-  "file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
-  "file_sha1": "数据集文件的 SHA-1 哈希值（可选，留空不影响训练）",
+  "file_name": "该目录下数据集文件夹或文件的名称（若上述参数未指定，则此项必需）",
+  "formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
+  "ranking": "是否为偏好数据集（可选，默认：False）",
   "subset": "数据集子集的名称（可选，默认：None）",
   "folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
-  "ranking": "是否为偏好数据集（可选，默认：False）",
-  "formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
+  "num_samples": "该数据集中用于训练的样本数量。（可选，默认：None）",
   "columns（可选）": {
     "prompt": "数据集代表提示词的表头名称（默认：instruction）",
     "query": "数据集代表请求的表头名称（默认：input）",
@@ -18,7 +20,11 @@
     "history": "数据集代表历史对话的表头名称（默认：None）",
     "messages": "数据集代表消息列表的表头名称（默认：conversations）",
     "system": "数据集代表系统提示的表头名称（默认：None）",
-    "tools": "数据集代表工具描述的表头名称（默认：None）"
+    "tools": "数据集代表工具描述的表头名称（默认：None）",
+    "images": "数据集代表图像输入的表头名称（默认：None）",
+    "chosen": "数据集代表更优回答的表头名称（默认：None）",
+    "rejected": "数据集代表更差回答的表头名称（默认：None）",
+    "kto_tag": "数据集代表 KTO 标签的表头名称（默认：None）"
   },
   "tags（可选，用于 sharegpt 格式）": {
     "role_tag": "消息中代表发送者身份的键名（默认：from）",
@@ -27,22 +33,28 @@
     "assistant_tag": "消息中代表助手的 role_tag（默认：gpt）",
     "observation_tag": "消息中代表工具返回结果的 role_tag（默认：observation）",
     "function_tag": "消息中代表工具调用的 role_tag（默认：function_call）",
-    "system_tag": "消息中代表系统提示的 role_tag（默认：system，会覆盖 system 列）"
+    "system_tag": "消息中代表系统提示的 role_tag（默认：system，会覆盖 system column）"
   }
 }
 ```
 
-添加后可通过指定 `--dataset 数据集名称` 参数使用自定义数据集。
+## Alpaca 格式
 
-----
+### 指令监督微调数据集
 
-该项目目前支持两种格式的数据集：**alpaca** 和 **sharegpt**，其中 alpaca 格式的数据集按照以下方式组织：
+- [样例数据集](alpaca_zh_demo.json)
+
+在指令监督微调时，`instruction` 列对应的内容会与 `input` 列对应的内容拼接后作为人类指令，即人类指令为 `instruction\ninput`。而 `output` 列对应的内容为模型回答。
+
+如果指定，`system` 列对应的内容将被作为系统提示词。
+
+`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮对话的指令和回答。注意在指令监督微调时，历史消息中的回答内容**也会被用于模型学习**。
 
 ```json
 [
   {
-    "instruction": "用户指令（必填）",
-    "input": "用户输入（选填）",
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
     "output": "模型回答（必填）",
     "system": "系统提示词（选填）",
     "history": [
@@ -53,10 +65,11 @@
 ]
 ```
 
-对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
 
 ```json
 "数据集名称": {
+  "file_name": "data.json",
   "columns": {
     "prompt": "instruction",
     "query": "input",
@@ -67,30 +80,135 @@
 }
 ```
 
-其中 `query` 列对应的内容会与 `prompt` 列对应的内容拼接后作为用户指令，即用户指令为 `prompt\nquery`。`response` 列对应的内容为模型回答。
+### 预训练数据集
 
-`system` 列对应的内容将被作为系统提示词。`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮的指令和回答。注意历史消息中的回答**也会被用于训练**。
+- [样例数据集](c4_demo.json)
 
-对于预训练数据集，仅 `prompt` 列中的内容会用于模型训练。
-
-对于偏好数据集，`response` 列应当是一个长度为 2 的字符串列表，排在前面的代表更优的回答，例如：
+在预训练时，只有 `text` 列中的内容会用于模型学习。
 
 ```json
-{
-  "instruction": "用户指令",
-  "input": "用户输入",
-  "output": [
-    "优质回答",
-    "劣质回答"
-  ]
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
 }
 ```
 
-添加偏好数据集需要额外指定 `"ranking": true`。
+### 偏好数据集
 
-----
+偏好数据集用于奖励模型训练、DPO 训练和 ORPO 训练。
 
-而 sharegpt 格式的数据集按照以下方式组织：
+它需要在 `chosen` 列中提供更优的回答，并在 `rejected` 列中提供更差的回答。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "chosen": "优质回答（必填）",
+    "rejected": "劣质回答（必填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### KTO 数据集
+
+- [样例数据集](kto_en_demo.json)
+
+KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "output": "模型回答（必填）",
+    "kto_tag": "人类反馈 [true/false]（必填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### 多模态数据集
+
+- [样例数据集](mllm_demo.json)
+
+多模态数据集需要额外添加一个 `images` 列，包含输入图像的路径。目前我们仅支持单张图像输入。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "output": "模型回答（必填）",
+    "images": [
+      "图像路径（必填）"
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "images": "images"
+  }
+}
+```
+
+## Sharegpt 格式
+
+### 指令监督微调数据集
+
+- [样例数据集](glaive_toolcall_zh_demo.json)
+
+相比 alpaca 格式的数据集，sharegpt 格式支持**更多的角色种类**，例如 human、gpt、observation、function 等等。它们构成一个对象列表呈现在 `conversations` 列中。
+
+注意其中 human 和 observation 必须出现在奇数位置，gpt 和 function 必须出现在偶数位置。
 
 ```json
 [
@@ -98,7 +216,15 @@
     "conversations": [
       {
         "from": "human",
-        "value": "用户指令"
+        "value": "人类指令"
+      },
+      {
+        "from": "function_call",
+        "value": "工具参数"
+      },
+      {
+        "from": "observation",
+        "value": "工具结果"
       },
       {
         "from": "gpt",
@@ -111,24 +237,114 @@
 ]
 ```
 
-对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
 
 ```json
 "数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
   "columns": {
     "messages": "conversations",
     "system": "system",
     "tools": "tools"
-  },
-  "tags": {
-    "role_tag": "from",
-    "content_tag": "value",
-    "user_tag": "human",
-    "assistant_tag": "gpt"
   }
 }
 ```
 
-其中 `messages` 列应当是一个列表，且符合 `用户/模型/用户/模型/用户/模型` 的顺序。
+### 偏好数据集
 
-预训练数据集和偏好数据集尚不支持 sharegpt 格式。
+- [样例数据集](dpo_zh_demo.json)
+
+Sharegpt 格式的偏好数据集同样需要在 `chosen` 列中提供更优的消息，并在 `rejected` 列中提供更差的消息。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      },
+      {
+        "from": "human",
+        "value": "人类指令"
+      }
+    ],
+    "chosen": {
+      "from": "gpt",
+      "value": "优质回答"
+    },
+    "rejected": {
+      "from": "gpt",
+      "value": "劣质回答"
+    }
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "ranking": true,
+  "columns": {
+    "messages": "conversations",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### OpenAI 格式
+
+OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消息可能是系统提示词。
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "系统提示词（选填）"
+      },
+      {
+        "role": "user",
+        "content": "人类指令"
+      },
+      {
+        "role": "assistant",
+        "content": "模型回答"
+      }
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "messages"
+  },
+  "tags": {
+    "role_tag": "role",
+    "content_tag": "content",
+    "user_tag": "user",
+    "assistant_tag": "assistant",
+    "system_tag": "system"
+  }
+}
+```
+
+Sharegpt 格式中的 KTO 数据集和多模态数据集与 alpaca 格式的类似。
+
+预训练数据集**不支持** sharegpt 格式。

data/alpaca_data_en_52k.json.REMOVED.git-id

@@ -1 +0,0 @@
-3779ddbc040543ab1834ef216c983d6fcc06cc9a

data/alpaca_data_zh_51k.json.REMOVED.git-id

@@ -1 +0,0 @@
-a97cf9475291591843976554878568e046d8a46d

data/alpaca_gpt4_data_en.json.REMOVED.git-id

@@ -1 +0,0 @@
-25508714b7879a1e5a6764ba7f979a980f549f1a

data/alpaca_gpt4_data_zh.json.REMOVED.git-id

@@ -1 +0,0 @@
-7cb6a7d11455bddc3d495750a2392683d775b184

data/comparison_gpt4_data_en.json.REMOVED.git-id

@@ -1 +0,0 @@
-f5cb08305ff5dc9c17a09809c54c8c8834aadc70

data/comparison_gpt4_data_zh.json.REMOVED.git-id

@@ -1 +0,0 @@
-aee47b7b443496e37808d7f34ef10403ff99bcc3

data/example_dataset/example_dataset.py

@@ -1,37 +0,0 @@
-import json
-from typing import Any, Dict, Generator, List, Tuple
-
-import datasets
-
-
-_DESCRIPTION = "An example of dataset."
-_CITATION = ""
-_HOMEPAGE = ""
-_LICENSE = ""
-_URL = "examples.json"
-
-
-class ExampleDataset(datasets.GeneratorBasedBuilder):
-    VERSION = datasets.Version("0.0.0")
-
-    def _info(self) -> datasets.DatasetInfo:
-        features = datasets.Features(
-            {
-                "instruction": datasets.Value("string"),
-                "input": datasets.Value("string"),
-                "output": datasets.Value("string"),
-                "history": datasets.Sequence(datasets.Sequence(datasets.Value("string"))),
-            }
-        )
-        return datasets.DatasetInfo(
-            description=_DESCRIPTION, features=features, homepage=_HOMEPAGE, license=_LICENSE, citation=_CITATION
-        )
-
-    def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
-        file_path = dl_manager.download(_URL)
-        return [datasets.SplitGenerator(name=datasets.Split.TRAIN, gen_kwargs={"filepath": file_path})]
-
-    def _generate_examples(self, filepath: str) -> Generator[Tuple[int, Dict[str, Any]], None, None]:
-        example_dataset = json.load(open(filepath, "r", encoding="utf-8"))
-        for key, example in enumerate(example_dataset):
-            yield key, example

data/glaive_toolcall_10k.json.REMOVED.git-id

@@ -1 +0,0 @@
-4748dff00d1dc42768a5b6cc772143c313017812

data/hh_rlhf_en/hh_rlhf_en.py

@@ -34,7 +34,8 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
         features = datasets.Features(
             {
                 "instruction": datasets.Value("string"),
-                "output": datasets.Sequence(datasets.Value("string")),
+                "chosen": datasets.Value("string"),
+                "rejected": datasets.Value("string"),
                 "history": datasets.Sequence(datasets.Sequence(datasets.Value("string"))),
             }
         )
@@ -79,5 +80,5 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
                             break
                         prompt = prompt[:human_idx]
 
-                    yield key, {"instruction": query, "output": [r_accept, r_reject], "history": history}
+                    yield key, {"instruction": query, "chosen": r_accept, "rejected": r_reject, "history": history}
                     key += 1

data/oaast_rm.json.REMOVED.git-id

@@ -1 +0,0 @@
-274079ea921762be356de85b18f13fa60b7ba8cb

data/oaast_sft.json.REMOVED.git-id

@@ -1 +0,0 @@
-57fd080be5bffe4153fe3ee26a175e3d56da30f3

data/orca_rlhf.json.REMOVED.git-id

@@ -1 +0,0 @@
-736bcedea2b24a1414765c6d69cbdafaea839f3c

data/wiki_demo.txt.REMOVED.git-id

@@ -1 +0,0 @@
-c9cf509b7fdac5490cfd6dae72c2d7b8a60af6cb

docker-compose.yml

@@ -10,8 +10,6 @@ services:
       - ./hf_cache:/root/.cache/huggingface/
       - ./data:/app/data
       - ./output:/app/output
-    environment:
-      - CUDA_VISIBLE_DEVICES=0
     ports:
       - "7860:7860"
     ipc: host

evaluation/ceval/ceval.py

@@ -19,7 +19,7 @@ import pandas as pd
 
 _CITATION = """\
 @article{huang2023ceval,
-  title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}, 
+  title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models},
   author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and Zhang, Junlei and Zhang, Jinghan and Su, Tangjun and Liu, Junteng and Lv, Chuancheng and Zhang, Yikai and Lei, Jiayi and Fu, Yao and Sun, Maosong and He, Junxian},
   journal={arXiv preprint arXiv:2305.08322},
   year={2023}
@@ -133,25 +133,19 @@ class Ceval(datasets.GeneratorBasedBuilder):
             datasets.SplitGenerator(
                 name=datasets.Split.TEST,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "test", f"{task_name}_test.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "test", f"{task_name}_test.csv"),
                 },
             ),
             datasets.SplitGenerator(
                 name=datasets.Split.VALIDATION,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "val", f"{task_name}_val.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "val", f"{task_name}_val.csv"),
                 },
             ),
             datasets.SplitGenerator(
                 name=datasets.Split.TRAIN,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "dev", f"{task_name}_dev.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "dev", f"{task_name}_dev.csv"),
                 },
             ),
         ]

evaluation/cmmlu/cmmlu.py

@@ -37,73 +37,73 @@ _LICENSE = "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 Internatio
 _URL = "cmmlu.zip"
 
 task_list = [
-     'agronomy',
-     'anatomy',
-     'ancient_chinese',
-     'arts',
-     'astronomy',
-     'business_ethics',
-     'chinese_civil_service_exam',
-     'chinese_driving_rule',
-     'chinese_food_culture',
-     'chinese_foreign_policy',
-     'chinese_history',
-     'chinese_literature',
-     'chinese_teacher_qualification',
-     'clinical_knowledge',
-     'college_actuarial_science',
-     'college_education',
-     'college_engineering_hydrology',
-     'college_law',
-     'college_mathematics',
-     'college_medical_statistics',
-     'college_medicine',
-     'computer_science',
-     'computer_security',
-     'conceptual_physics',
-     'construction_project_management',
-     'economics',
-     'education',
-     'electrical_engineering',
-     'elementary_chinese',
-     'elementary_commonsense',
-     'elementary_information_and_technology',
-     'elementary_mathematics',
-     'ethnology',
-     'food_science',
-     'genetics',
-     'global_facts',
-     'high_school_biology',
-     'high_school_chemistry',
-     'high_school_geography',
-     'high_school_mathematics',
-     'high_school_physics',
-     'high_school_politics',
-     'human_sexuality',
-     'international_law',
-     'journalism',
-     'jurisprudence',
-     'legal_and_moral_basis',
-     'logical',
-     'machine_learning',
-     'management',
-     'marketing',
-     'marxist_theory',
-     'modern_chinese',
-     'nutrition',
-     'philosophy',
-     'professional_accounting',
-     'professional_law',
-     'professional_medicine',
-     'professional_psychology',
-     'public_relations',
-     'security_study',
-     'sociology',
-     'sports_science',
-     'traditional_chinese_medicine',
-     'virology',
-     'world_history',
-     'world_religions',
+    "agronomy",
+    "anatomy",
+    "ancient_chinese",
+    "arts",
+    "astronomy",
+    "business_ethics",
+    "chinese_civil_service_exam",
+    "chinese_driving_rule",
+    "chinese_food_culture",
+    "chinese_foreign_policy",
+    "chinese_history",
+    "chinese_literature",
+    "chinese_teacher_qualification",
+    "clinical_knowledge",
+    "college_actuarial_science",
+    "college_education",
+    "college_engineering_hydrology",
+    "college_law",
+    "college_mathematics",
+    "college_medical_statistics",
+    "college_medicine",
+    "computer_science",
+    "computer_security",
+    "conceptual_physics",
+    "construction_project_management",
+    "economics",
+    "education",
+    "electrical_engineering",
+    "elementary_chinese",
+    "elementary_commonsense",
+    "elementary_information_and_technology",
+    "elementary_mathematics",
+    "ethnology",
+    "food_science",
+    "genetics",
+    "global_facts",
+    "high_school_biology",
+    "high_school_chemistry",
+    "high_school_geography",
+    "high_school_mathematics",
+    "high_school_physics",
+    "high_school_politics",
+    "human_sexuality",
+    "international_law",
+    "journalism",
+    "jurisprudence",
+    "legal_and_moral_basis",
+    "logical",
+    "machine_learning",
+    "management",
+    "marketing",
+    "marxist_theory",
+    "modern_chinese",
+    "nutrition",
+    "philosophy",
+    "professional_accounting",
+    "professional_law",
+    "professional_medicine",
+    "professional_psychology",
+    "public_relations",
+    "security_study",
+    "sociology",
+    "sports_science",
+    "traditional_chinese_medicine",
+    "virology",
+    "world_history",
+    "world_religions",
 ]
 
 

evaluation/mmlu/mmlu.py

@@ -136,31 +136,25 @@ class MMLU(datasets.GeneratorBasedBuilder):
             datasets.SplitGenerator(
                 name=datasets.Split.TEST,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "data", "test", f"{task_name}_test.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "data", "test", f"{task_name}_test.csv"),
                 },
             ),
             datasets.SplitGenerator(
                 name=datasets.Split.VALIDATION,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "data", "val", f"{task_name}_val.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "data", "val", f"{task_name}_val.csv"),
                 },
             ),
             datasets.SplitGenerator(
                 name=datasets.Split.TRAIN,
                 gen_kwargs={
-                    "filepath": os.path.join(
-                        data_dir, "data", "dev", f"{task_name}_dev.csv"
-                    ),
+                    "filepath": os.path.join(data_dir, "data", "dev", f"{task_name}_dev.csv"),
                 },
             ),
         ]
 
     def _generate_examples(self, filepath):
-        df = pd.read_csv(filepath)
+        df = pd.read_csv(filepath, header=None)
         df.columns = ["question", "A", "B", "C", "D", "answer"]
 
         for i, instance in enumerate(df.to_dict(orient="records")):

examples/README.md

@@ -1,48 +1,233 @@
 We provide diverse examples about fine-tuning LLMs.
 
+Make sure to execute these commands in the `LLaMA-Factory` directory.
+
+## Table of Contents
+
+- [LoRA Fine-Tuning on A Single GPU](#lora-fine-tuning-on-a-single-gpu)
+- [QLoRA Fine-Tuning on a Single GPU](#qlora-fine-tuning-on-a-single-gpu)
+- [LoRA Fine-Tuning on Multiple GPUs](#lora-fine-tuning-on-multiple-gpus)
+- [LoRA Fine-Tuning on Multiple NPUs](#lora-fine-tuning-on-multiple-npus)
+- [Full-Parameter Fine-Tuning on Multiple GPUs](#full-parameter-fine-tuning-on-multiple-gpus)
+- [Merging LoRA Adapters and Quantization](#merging-lora-adapters-and-quantization)
+- [Inferring LoRA Fine-Tuned Models](#inferring-lora-fine-tuned-models)
+- [Extras](#extras)
+
+## Examples
+
+### LoRA Fine-Tuning on A Single GPU
+
+#### (Continuous) Pre-Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_pretrain.yaml
 ```
-examples/
-├── lora_single_gpu/
-│   ├── pretrain.sh: Do continuous pre-training using LoRA
-│   ├── sft.sh: Do supervised fine-tuning using LoRA
-│   ├── reward.sh: Do reward modeling using LoRA
-│   ├── ppo.sh: Do PPO training using LoRA
-│   ├── dpo.sh: Do DPO training using LoRA
-│   ├── orpo.sh: Do ORPO training using LoRA
-│   ├── prepare.sh: Save tokenized dataset
-│   └── predict.sh: Do batch predict and compute BLEU and ROUGE scores after LoRA tuning
-├── qlora_single_gpu/
-│   ├── bitsandbytes.sh: Fine-tune 4/8-bit BNB models using QLoRA
-│   ├── gptq.sh: Fine-tune 4/8-bit GPTQ models using QLoRA
-│   ├── awq.sh: Fine-tune 4-bit AWQ models using QLoRA
-│   └── aqlm.sh: Fine-tune 2-bit AQLM models using QLoRA
-├── lora_multi_gpu/
-│   ├── single_node.sh: Fine-tune model with Accelerate on single node using LoRA
-│   └── multi_node.sh: Fine-tune model with Accelerate on multiple nodes using LoRA
-├── full_multi_gpu/
-│   ├── single_node.sh: Full fine-tune model with DeepSpeed on single node
-│   ├── multi_node.sh: Full fine-tune model with DeepSpeed on multiple nodes
-│   └── predict.sh: Do batch predict and compute BLEU and ROUGE scores after full tuning
-├── merge_lora/
-│   ├── merge.sh: Merge LoRA weights into the pre-trained models
-│   └── quantize.sh: Quantize the fine-tuned model with AutoGPTQ
-├── inference/
-│   ├── cli_demo.sh: Launch a command line interface with LoRA adapters
-│   ├── api_demo.sh: Launch an OpenAI-style API with LoRA adapters
-│   ├── web_demo.sh: Launch a web interface with LoRA adapters
-│   └── evaluate.sh: Evaluate model on the MMLU/CMMLU/C-Eval benchmarks with LoRA adapters
-└── extras/
-    ├── galore/
-    │   └── sft.sh: Fine-tune model with GaLore
-    ├── badam/
-    │   └── sft.sh: Fine-tune model with BAdam
-    ├── loraplus/
-    │   └── sft.sh: Fine-tune model using LoRA+
-    ├── mod/
-    │   └── sft.sh: Fine-tune model using Mixture-of-Depths
-    ├── llama_pro/
-    │   ├── expand.sh: Expand layers in the model
-    │   └── sft.sh: Fine-tune the expanded model
-    └── fsdp_qlora/
-        └── sft.sh: Fine-tune quantized model with FSDP+QLoRA
+
+#### Supervised Fine-Tuning
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
+```
+
+#### Multimodal Supervised Fine-Tuning
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
+```
+
+#### Reward Modeling
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_reward.yaml
+```
+
+#### PPO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_ppo.yaml
+```
+
+#### DPO/ORPO/SimPO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_dpo.yaml
+```
+
+#### KTO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_kto.yaml
+```
+
+#### Preprocess Dataset
+
+It is useful for large dataset, use `tokenized_path` in config to load the preprocessed dataset.
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_preprocess.yaml
+```
+
+#### Evaluating on MMLU/CMMLU/C-Eval Benchmarks
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli eval examples/lora_single_gpu/llama3_lora_eval.yaml
+```
+
+#### Batch Predicting and Computing BLEU and ROUGE Scores
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_predict.yaml
+```
+
+### QLoRA Fine-Tuning on a Single GPU
+
+#### Supervised Fine-Tuning with 4/8-bit Bitsandbytes Quantization (Recommended)
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml
+```
+
+#### Supervised Fine-Tuning with 4/8-bit GPTQ Quantization
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml
+```
+
+#### Supervised Fine-Tuning with 4-bit AWQ Quantization
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_awq.yaml
+```
+
+#### Supervised Fine-Tuning with 2-bit AQLM Quantization
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml
+```
+
+### LoRA Fine-Tuning on Multiple GPUs
+
+#### Supervised Fine-Tuning on Single Node
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+```
+
+#### Supervised Fine-Tuning on Multiple Nodes
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+```
+
+#### Supervised Fine-Tuning with DeepSpeed ZeRO-3 (Weight Sharding)
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft_ds.yaml
+```
+
+### LoRA Fine-Tuning on Multiple NPUs
+
+#### Supervised Fine-Tuning with DeepSpeed ZeRO-0
+
+```bash
+ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_npu/llama3_lora_sft_ds.yaml
+```
+
+### Full-Parameter Fine-Tuning on Multiple GPUs
+
+#### Supervised Fine-Tuning on Single Node
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+```
+
+#### Supervised Fine-Tuning on Multiple Nodes
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+```
+
+#### Batch Predicting and Computing BLEU and ROUGE Scores
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/full_multi_gpu/llama3_full_predict.yaml
+```
+
+### Merging LoRA Adapters and Quantization
+
+#### Merge LoRA Adapters
+
+Note: DO NOT use quantized model or `quantization_bit` when merging LoRA adapters.
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### Quantizing Model using AutoGPTQ
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
+```
+
+### Inferring LoRA Fine-Tuned Models
+
+Use `CUDA_VISIBLE_DEVICES=0,1` to infer models on multiple devices.
+
+#### Use CLI
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+```
+
+#### Use Web UI
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
+```
+
+#### Launch OpenAI-style API
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli api examples/inference/llama3_lora_sft.yaml
+```
+
+### Extras
+
+#### Full-Parameter Fine-Tuning using GaLore
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/galore/llama3_full_sft.yaml
+```
+
+#### Full-Parameter Fine-Tuning using BAdam
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/badam/llama3_full_sft.yaml
+```
+
+#### LoRA+ Fine-Tuning
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/loraplus/llama3_lora_sft.yaml
+```
+
+#### Mixture-of-Depths Fine-Tuning
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/mod/llama3_full_sft.yaml
+```
+
+#### LLaMA-Pro Fine-Tuning
+
+```bash
+bash examples/extras/llama_pro/expand.sh
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
+```
+
+#### FSDP+QLoRA Fine-Tuning
+
+```bash
+bash examples/extras/fsdp_qlora/single_node.sh
 ```

examples/README_zh.md

@@ -1,48 +1,233 @@
 我们提供了多样化的大模型微调示例脚本。
 
+请确保在 `LLaMA-Factory` 目录下执行下述命令。
+
+## 目录
+
+- [单 GPU LoRA 微调](#单-gpu-lora-微调)
+- [单 GPU QLoRA 微调](#单-gpu-qlora-微调)
+- [多 GPU LoRA 微调](#多-gpu-lora-微调)
+- [多 NPU LoRA 微调](#多-npu-lora-微调)
+- [多 GPU 全参数微调](#多-gpu-全参数微调)
+- [合并 LoRA 适配器与模型量化](#合并-lora-适配器与模型量化)
+- [推理 LoRA 模型](#推理-lora-模型)
+- [杂项](#杂项)
+
+## 示例
+
+### 单 GPU LoRA 微调
+
+#### （增量）预训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_pretrain.yaml
 ```
-examples/
-├── lora_single_gpu/
-│   ├── pretrain.sh: 基于 LoRA 进行增量预训练
-│   ├── sft.sh: 基于 LoRA 进行指令监督微调
-│   ├── reward.sh: 基于 LoRA 进行奖励模型训练
-│   ├── ppo.sh: 基于 LoRA 进行 PPO 训练
-│   ├── dpo.sh: 基于 LoRA 进行 DPO 训练
-│   ├── orpo.sh: 基于 LoRA 进行 ORPO 训练
-│   ├── prepare.sh: 保存预处理后的数据集
-│   └── predict.sh: 基于 LoRA 进行批量预测并计算 BLEU 和 ROUGE 分数
-├── qlora_single_gpu/
-│   ├── bitsandbytes.sh: 基于 QLoRA 微调 4/8 比特 BNB 模型
-│   ├── gptq.sh: 基于 QLoRA 微调 4/8 比特 GPTQ 模型
-│   ├── awq.sh: 基于 QLoRA 微调 4 比特 AWQ 模型
-│   └── aqlm.sh: 基于 QLoRA 微调 2 比特 AQLM 模型
-├── lora_multi_gpu/
-│   ├── single_node.sh: 使用 Accelerate 进行单节点 LoRA 训练
-│   └── multi_node.sh: 使用 Accelerate 进行多节点 LoRA 训练
-├── full_multi_gpu/
-│   ├── single_node.sh: 使用 DeepSpeed 进行单节点全量训练
-│   ├── multi_node.sh: 使用 DeepSpeed 进行多节点全量训练
-│   └── predict.sh: 基于全量训练进行批量预测并计算 BLEU 和 ROUGE 分数
-├── merge_lora/
-│   ├── merge.sh: 将 LoRA 权重合并到预训练模型中
-│   └── quantize.sh: 使用 AutoGPTQ 量化微调后的模型
-├── inference/
-│   ├── cli_demo.sh: 启动 LoRA 模型的命令行推理接口
-│   ├── api_demo.sh: 启动 LoRA 模型的 OpenAI 风格 API
-│   ├── web_demo.sh: 启动 LoRA 模型的浏览器推理接口
-│   └── evaluate.sh: 在 MMLU/CMMLU/C-Eval 数据集上评测 LoRA 模型
-└── extras/
-    ├── galore/
-    │   └── sft.sh: 使用 GaLore 训练模型
-    ├── badam/
-    │   └── sft.sh: 使用 BAdam 训练模型
-    ├── loraplus/
-    │   └── sft.sh: 使用 LoRA+ 训练模型
-    ├── mod/
-    │   └── sft.sh: 使用深度混合训练模型
-    ├── llama_pro/
-    │   ├── expand.sh: 扩展模型中的层
-    │   └── sft.sh: 训练扩展后的模型
-    └── fsdp_qlora/
-        └── sft.sh: 使用 FSDP+QLoRA 微调量化模型
+
+#### 指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
+```
+
+#### 多模态指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
+```
+
+#### 奖励模型训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_reward.yaml
+```
+
+#### PPO 训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_ppo.yaml
+```
+
+#### DPO/ORPO/SimPO 训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_dpo.yaml
+```
+
+#### KTO 训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_kto.yaml
+```
+
+#### 预处理数据集
+
+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
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_preprocess.yaml
+```
+
+#### 在 MMLU/CMMLU/C-Eval 上评估
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli eval examples/lora_single_gpu/llama3_lora_eval.yaml
+```
+
+#### 批量预测并计算 BLEU 和 ROUGE 分数
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_predict.yaml
+```
+
+### 单 GPU QLoRA 微调
+
+#### 基于 4/8 比特 Bitsandbytes 量化进行指令监督微调（推荐）
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml
+```
+
+#### 基于 4/8 比特 GPTQ 量化进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml
+```
+
+#### 基于 4 比特 AWQ 量化进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_awq.yaml
+```
+
+#### 基于 2 比特 AQLM 量化进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml
+```
+
+### 多 GPU LoRA 微调
+
+#### 在单机上进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+```
+
+#### 在多机上进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
+```
+
+#### 使用 DeepSpeed ZeRO-3 平均分配显存
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft_ds.yaml
+```
+
+### 多 NPU LoRA 微调
+
+#### 使用 DeepSpeed ZeRO-0 进行指令监督微调
+
+```bash
+ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_npu/llama3_lora_sft_ds.yaml
+```
+
+### 多 GPU 全参数微调
+
+#### 在单机上进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+```
+
+#### 在多机上进行指令监督微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
+```
+
+#### 批量预测并计算 BLEU 和 ROUGE 分数
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/full_multi_gpu/llama3_full_predict.yaml
+```
+
+### 合并 LoRA 适配器与模型量化
+
+#### 合并 LoRA 适配器
+
+注：请勿使用量化后的模型或 `quantization_bit` 参数来合并 LoRA 适配器。
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### 使用 AutoGPTQ 量化模型
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
+```
+
+### 推理 LoRA 模型
+
+使用 `CUDA_VISIBLE_DEVICES=0,1` 进行多卡推理。
+
+#### 使用命令行接口
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
+```
+
+#### 使用浏览器界面
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
+```
+
+#### 启动 OpenAI 风格 API
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli api examples/inference/llama3_lora_sft.yaml
+```
+
+### 杂项
+
+#### 使用 GaLore 进行全参数训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/galore/llama3_full_sft.yaml
+```
+
+#### 使用 BAdam 进行全参数训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/badam/llama3_full_sft.yaml
+```
+
+#### LoRA+ 微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/loraplus/llama3_lora_sft.yaml
+```
+
+#### 深度混合微调
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/mod/llama3_full_sft.yaml
+```
+
+#### LLaMA-Pro 微调
+
+```bash
+bash examples/extras/llama_pro/expand.sh
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
+```
+
+#### FSDP+QLoRA 微调
+
+```bash
+bash examples/extras/fsdp_qlora/single_node.sh
 ```

examples/accelerate/fsdp_config.yaml

@@ -5,16 +5,16 @@ downcast_bf16: 'no'
 fsdp_config:
   fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
   fsdp_backward_prefetch: BACKWARD_PRE
-  fsdp_cpu_ram_efficient_loading: true
   fsdp_forward_prefetch: false
-  fsdp_offload_params: true
+  fsdp_cpu_ram_efficient_loading: true
+  fsdp_offload_params: true # offload may affect training speed
   fsdp_sharding_strategy: FULL_SHARD
   fsdp_state_dict_type: FULL_STATE_DICT
   fsdp_sync_module_states: true
-  fsdp_use_orig_params: false
+  fsdp_use_orig_params: true
 machine_rank: 0
 main_training_function: main
-mixed_precision: fp16
+mixed_precision: fp16 # or bf16
 num_machines: 1 # the number of nodes
 num_processes: 2 # the number of GPUs in all nodes
 rdzv_backend: static

examples/accelerate/master_config.yaml

@@ -1,18 +0,0 @@
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: MULTI_GPU
-downcast_bf16: 'no'
-gpu_ids: all
-machine_rank: 0
-main_process_ip: 192.168.0.1
-main_process_port: 29555
-main_training_function: main
-mixed_precision: fp16
-num_machines: 2 # the number of nodes
-num_processes: 16 # the number of GPUs in all nodes
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false

examples/accelerate/single_config.yaml

@@ -1,16 +0,0 @@
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: MULTI_GPU
-downcast_bf16: 'no'
-gpu_ids: all
-machine_rank: 0
-main_training_function: main
-mixed_precision: fp16
-num_machines: 1 # the number of nodes
-num_processes: 4 # the number of GPUs in all nodes
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false

examples/accelerate/slave_config.yaml

@@ -1,18 +0,0 @@
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: MULTI_GPU
-downcast_bf16: 'no'
-gpu_ids: all
-machine_rank: 1
-main_process_ip: 192.168.0.1
-main_process_port: 29555
-main_training_function: main
-mixed_precision: fp16
-num_machines: 2 # the number of nodes
-num_processes: 16 # the number of GPUs in all nodes
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false

examples/extras/MoD/sft.sh

@@ -1,33 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../../data \
-    --template default \
-    --finetuning_type full \
-    --mixture_of_depths convert \
-    --output_dir ../../../saves/LLaMA2-7B/mod/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --optim paged_adamw_8bit \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --pure_bf16

examples/extras/badam/llama3_lora_sft.yaml

@@ -0,0 +1,41 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+use_badam: true
+badam_switch_mode: ascending
+badam_switch_interval: 50
+badam_verbose: 2
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+pure_bf16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/extras/badam/sft.sh

@@ -1,35 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../../data \
-    --template default \
-    --finetuning_type full \
-    --use_badam \
-    --badam_switch_mode descending \
-    --badam_switch_block_every 50 \
-    --badam_verbose 2 \
-    --output_dir ../../../saves/LLaMA2-7B/badam/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --pure_bf16

examples/extras/fsdp_qlora/llama3_lora_sft.yaml

@@ -0,0 +1,42 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+quantization_bit: 4
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### ddp
+ddp_timeout: 180000000
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/extras/fsdp_qlora/sft.sh

@@ -1,40 +0,0 @@
-#!/bin/bash
-
-pip install "transformers>=4.39.1"
-pip install "accelerate>=0.28.0"
-pip install "bitsandbytes>=0.43.0"
-
-CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
-    --config_file ../../accelerate/fsdp_config.yaml \
-    ../../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-70b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../../saves/LLaMA2-70B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 4 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --ddp_timeout 180000000 \
-    --quantization_bit 4 \
-    --plot_loss \
-    --fp16

examples/extras/fsdp_qlora/single_node.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+# DO NOT use GPTQ/AWQ model in FSDP+QLoRA
+
+CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
+    --config_file examples/accelerate/fsdp_config.yaml \
+    src/train.py examples/extras/fsdp_qlora/llama3_lora_sft.yaml

examples/extras/galore/llama3_full_sft.yaml

@@ -0,0 +1,42 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+use_galore: true
+galore_layerwise: true
+galore_target: mlp,self_attn
+galore_rank: 128
+galore_scale: 2.0
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 1
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+pure_bf16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/extras/galore/sft.sh

@@ -1,36 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../../data \
-    --template default \
-    --finetuning_type full \
-    --use_galore \
-    --galore_layerwise \
-    --galore_target mlp,self_attn \
-    --galore_rank 128 \
-    --galore_scale 2.0 \
-    --output_dir ../../../saves/LLaMA2-7B/galore/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 1 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --pure_bf16

examples/extras/llama_pro/expand.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-python ../../../scripts/llama_pro.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --output_dir ../../../models/llama2-7b-pro \
+python scripts/llama_pro.py \
+    --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct \
+    --output_dir models/llama3-8b-instruct-pro \
     --num_expand 8

examples/extras/llama_pro/llama3_freeze_sft.yaml

@@ -0,0 +1,40 @@
+### model
+model_name_or_path: models/llama3-8b-instruct-pro
+
+### method
+stage: sft
+do_train: true
+finetuning_type: freeze
+freeze_trainable_layers: 8
+freeze_trainable_modules: all
+use_llama_pro: true
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b-instruct-pro/freeze/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/extras/llama_pro/sft.sh

@@ -1,34 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path ../../../models/llama2-7b-pro \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../../data \
-    --template default \
-    --finetuning_type freeze \
-    --name_module_trainable all \
-    --num_layer_trainable 8 \
-    --use_llama_pro \
-    --output_dir ../../../saves/LLaMA2-7B-Pro/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/extras/loraplus/llama3_lora_sft.yaml

@@ -0,0 +1,39 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+loraplus_lr_ratio: 16.0
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/extras/loraplus/sft.sh

@@ -1,33 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --loraplus_lr_ratio 16.0 \
-    --output_dir ../../saves/LLaMA2-7B/loraplus/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/extras/mod/llama3_full_sft.yaml

@@ -0,0 +1,39 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+mixture_of_depths: convert
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b-mod/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+optim: paged_adamw_8bit
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+pure_bf16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/full_multi_gpu/llama3_full_predict.yaml

@@ -0,0 +1,23 @@
+### model
+model_name_or_path: saves/llama3-8b/full/sft
+
+### method
+stage: sft
+do_predict: true
+finetuning_type: full
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 50
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/full/predict
+overwrite_output_dir: true
+
+### eval
+per_device_eval_batch_size: 1
+predict_with_generate: true

examples/full_multi_gpu/llama3_full_sft.yaml

@@ -0,0 +1,41 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+
+### ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/full_multi_gpu/multi_node.sh

@@ -1,38 +0,0 @@
-#!/bin/bash
-
-python -m torch.distributed.run \
-    --nproc_per_node $NPROC_PER_NODE \
-    --nnodes $NNODES \
-    --node_rank $RANK \
-    --master_addr $MASTER_ADDR \
-    --master_port $MASTER_PORT \
-    ../../src/train_bash.py \
-    --deepspeed ../deepspeed/ds_z3_config.json \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type full \
-    --output_dir ../../saves/LLaMA2-7B/full/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 2 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --ddp_timeout 180000000 \
-    --plot_loss \
-    --fp16

examples/full_multi_gpu/predict.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_predict \
-    --model_name_or_path ../../saves/LLaMA2-7B/full/sft \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type full \
-    --output_dir ../../saves/LLaMA2-7B/full/predict \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_eval_batch_size 1 \
-    --max_samples 20 \
-    --predict_with_generate

examples/full_multi_gpu/single_node.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-
-deepspeed --num_gpus 4 ../../src/train_bash.py \
-    --deepspeed ../deepspeed/ds_z3_config.json \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type full \
-    --output_dir ../../saves/LLaMA2-7B/full/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 2 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --ddp_timeout 180000000 \
-    --plot_loss \
-    --fp16

examples/inference/api_demo.sh

@@ -1,7 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python ../../src/api_demo.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora

examples/inference/cli_demo.sh

@@ -1,7 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/cli_demo.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora

examples/inference/evaluate.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/evaluate.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template fewshot \
-    --finetuning_type lora \
-    --task mmlu \
-    --split test \
-    --lang en \
-    --n_shot 5 \
-    --batch_size 4

examples/inference/llama3.yaml

@@ -0,0 +1,2 @@
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3

examples/inference/llama3_lora_sft.yaml

@@ -0,0 +1,4 @@
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+template: llama3
+finetuning_type: lora

examples/inference/llama3_vllm.yaml

@@ -0,0 +1,4 @@
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+infer_backend: vllm
+vllm_enforce_eager: true

examples/inference/web_demo.sh

@@ -1,7 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/web_demo.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora

examples/lora_multi_gpu/llama3_lora_sft.yaml

@@ -0,0 +1,41 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### ddp
+ddp_timeout: 180000000
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_multi_gpu/llama3_lora_sft_ds.yaml

@@ -0,0 +1,42 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_multi_gpu/multi_node.sh

@@ -1,35 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
-    --config_file ../accelerate/master_config.yaml \
-    ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 2 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --ddp_timeout 180000000 \
-    --plot_loss \
-    --fp16

examples/lora_multi_gpu/single_node.sh

@@ -1,35 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch \
-    --config_file ../accelerate/single_config.yaml \
-    ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 2 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --ddp_timeout 180000000 \
-    --plot_loss \
-    --fp16

examples/lora_multi_npu/llama3_lora_sft_ds.yaml

@@ -0,0 +1,42 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z0_config.json
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/dpo.sh

@@ -1,35 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage dpo \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --create_new_adapter \
-    --dataset orca_rlhf \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/dpo \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 1e-5 \
-    --num_train_epochs 1.0 \
-    --max_samples 1000 \
-    --val_size 0.1 \
-    --dpo_ftx 1.0 \
-    --plot_loss \
-    --fp16

examples/lora_single_gpu/llama3_lora_dpo.yaml

@@ -0,0 +1,40 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: dpo
+do_train: true
+finetuning_type: lora
+lora_target: all
+pref_beta: 0.1
+pref_loss: sigmoid  # [sigmoid (dpo), orpo, simpo]
+
+### dataset
+dataset: dpo_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/dpo
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 5.0e-6
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/llama3_lora_eval.yaml

@@ -0,0 +1,19 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+
+### method
+finetuning_type: lora
+
+### dataset
+task: mmlu
+split: test
+template: fewshot
+lang: en
+n_shot: 5
+
+### output
+save_dir: saves/llama3-8b/lora/eval
+
+### eval
+batch_size: 4

examples/lora_single_gpu/llama3_lora_kto.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: kto
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: kto_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/kto
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 5.0e-6
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/llama3_lora_ppo.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+reward_model: saves/llama3-8b/lora/reward
+
+### method
+stage: ppo
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/ppo
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### generate
+max_new_tokens: 512
+top_k: 0
+top_p: 0.9

examples/lora_single_gpu/llama3_lora_predict.yaml

@@ -0,0 +1,24 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+
+### method
+stage: sft
+do_predict: true
+finetuning_type: lora
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 50
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/predict
+overwrite_output_dir: true
+
+### eval
+per_device_eval_batch_size: 1
+predict_with_generate: true

examples/lora_single_gpu/llama3_lora_pretrain.yaml

@@ -0,0 +1,37 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: pt
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: c4_demo
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/llama3_lora_reward.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: rm
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: dpo_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/reward
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/llama3_lora_sft.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/llama3_preprocess.yaml

@@ -0,0 +1,21 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+tokenized_path: saves/llama3-8b/dataset/sft
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+overwrite_output_dir: true

examples/lora_single_gpu/llava1_5_lora_sft.yaml

@@ -0,0 +1,39 @@
+### model
+model_name_or_path: llava-hf/llava-1.5-7b-hf
+visual_inputs: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: mllm_demo
+template: vicuna
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llava1_5-7b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/lora_single_gpu/orpo.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage orpo \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset orca_rlhf \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/orpo \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 1e-5 \
-    --num_train_epochs 1.0 \
-    --max_samples 1000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/lora_single_gpu/ppo.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage ppo \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --create_new_adapter \
-    --dataset alpaca_gpt4_en \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --reward_model ../../saves/LLaMA2-7B/lora/reward \
-    --output_dir ../../saves/LLaMA2-7B/lora/ppo \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 512 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --save_steps 100 \
-    --learning_rate 1e-5 \
-    --num_train_epochs 1.0 \
-    --max_samples 1000 \
-    --top_k 0 \
-    --top_p 0.9 \
-    --max_new_tokens 256 \
-    --plot_loss \
-    --fp16

examples/lora_single_gpu/predict.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_predict \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft,../../saves/LLaMA2-7B/lora/dpo \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --output_dir ../../saves/LLaMA2-7B/lora/predict \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_eval_batch_size 1 \
-    --max_samples 20 \
-    --predict_with_generate

examples/lora_single_gpu/prepare.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES= python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --max_samples 3000 \
-    --tokenized_path ../../saves/datasets/sft

examples/lora_single_gpu/pretrain.sh

@@ -1,31 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage pt \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset c4_demo \
-    --dataset_dir ../../data \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/pretrain \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 10000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/lora_single_gpu/reward.sh

@@ -1,33 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage rm \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --create_new_adapter \
-    --dataset orca_rlhf \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/reward \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --learning_rate 1e-5 \
-    --num_train_epochs 1.0 \
-    --max_samples 5000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/lora_single_gpu/sft.sh

@@ -1,32 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --preprocessing_num_workers 16 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --warmup_steps 20 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/merge_lora/llama3_gptq.yaml

@@ -0,0 +1,11 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+
+### export
+export_dir: models/llama3_gptq
+export_quantization_bit: 4
+export_quantization_dataset: data/c4_demo.json
+export_size: 2
+export_device: cpu
+export_legacy_format: false

examples/merge_lora/llama3_lora_sft.yaml

@@ -0,0 +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
+adapter_name_or_path: saves/llama3-8b/lora/sft
+template: llama3
+finetuning_type: lora
+
+### export
+export_dir: models/llama3_lora_sft
+export_size: 2
+export_device: cpu
+export_legacy_format: false

examples/merge_lora/merge.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-# DO NOT use quantized model or quantization_bit when merging lora weights
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora \
-    --export_dir ../../models/llama2-7b-sft \
-    --export_size 2 \
-    --export_legacy_format False

examples/merge_lora/quantize.sh

@@ -1,10 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
-    --model_name_or_path ../../models/llama2-7b-sft \
-    --template default \
-    --export_dir ../../models/llama2-7b-sft-int4 \
-    --export_quantization_bit 4 \
-    --export_quantization_dataset ../../data/c4_demo.json \
-    --export_size 2 \
-    --export_legacy_format False

examples/qlora_single_gpu/aqlm.sh

@@ -1,30 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path BlackSamorez/Llama-2-7b-AQLM-2Bit-1x16-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/qlora_single_gpu/awq.sh

@@ -1,30 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path TheBloke/Llama-2-7B-AWQ \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/qlora_single_gpu/bitsandbytes.sh

@@ -1,31 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --quantization_bit 4 \
-    --plot_loss \
-    --fp16

examples/qlora_single_gpu/gptq.sh

@@ -1,30 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
-    --stage sft \
-    --do_train \
-    --model_name_or_path TheBloke/Llama-2-7B-GPTQ \
-    --dataset alpaca_gpt4_en,glaive_toolcall \
-    --dataset_dir ../../data \
-    --template default \
-    --finetuning_type lora \
-    --lora_target q_proj,v_proj \
-    --output_dir ../../saves/LLaMA2-7B/lora/sft \
-    --overwrite_cache \
-    --overwrite_output_dir \
-    --cutoff_len 1024 \
-    --per_device_train_batch_size 1 \
-    --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
-    --lr_scheduler_type cosine \
-    --logging_steps 10 \
-    --save_steps 100 \
-    --eval_steps 100 \
-    --evaluation_strategy steps \
-    --load_best_model_at_end \
-    --learning_rate 5e-5 \
-    --num_train_epochs 3.0 \
-    --max_samples 3000 \
-    --val_size 0.1 \
-    --plot_loss \
-    --fp16

examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_awq.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: TechxGenus/Meta-Llama-3-8B-Instruct-AWQ
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml

@@ -0,0 +1,39 @@
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+quantization_bit: 4
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml

@@ -0,0 +1,38 @@
+### model
+model_name_or_path: TechxGenus/Meta-Llama-3-8B-Instruct-GPTQ
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### 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
+fp16: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

pyproject.toml

@@ -13,7 +13,7 @@ select = ["C", "E", "F", "I", "W"]
 
 [tool.ruff.lint.isort]
 lines-after-imports = 2
-known-first-party = ["llmtuner"]
+known-first-party = ["llamafactory"]
 known-third-party = [
     "accelerate",
     "datasets",

requirements.txt

@@ -1,17 +1,19 @@
-torch>=1.13.1
-transformers>=4.37.2
-datasets>=2.14.3
-accelerate>=0.27.2
-peft>=0.10.0
-trl>=0.8.1
+transformers>=4.41.2
+datasets>=2.16.0
+accelerate>=0.30.1
+peft>=0.11.1
+trl>=0.8.6
 gradio>=4.0.0
 scipy
 einops
 sentencepiece
+tiktoken
 protobuf
 uvicorn
 pydantic
 fastapi
 sse-starlette
-matplotlib
+matplotlib>=3.7.0
 fire
+packaging
+pyyaml

scripts/cal_flops.py

@@ -3,24 +3,22 @@
 # Usage: python cal_flops.py --model_name_or_path path_to_model --batch_size 1 --seq_length 512
 # Inspired by: https://www.deepspeed.ai/tutorials/flops-profiler/
 
-from typing import Optional
-
 import fire
 import torch
 from deepspeed.accelerator import get_accelerator  # type: ignore
 from deepspeed.profiling.flops_profiler import get_model_profile  # type: ignore
 
-from llmtuner import ChatModel
+from llamafactory.chat import ChatModel
 
 
 def calculate_flops(
     model_name_or_path: str,
-    batch_size: Optional[int] = 1,
-    seq_length: Optional[int] = 256,
-    flash_attn: Optional[bool] = False,
+    batch_size: int = 1,
+    seq_length: int = 256,
+    flash_attn: str = "auto",
 ):
     with get_accelerator().device(0):
-        chat_model = ChatModel(dict(model_name_or_path=model_name_or_path, template="vanilla", flash_attn=flash_attn))
+        chat_model = ChatModel(dict(model_name_or_path=model_name_or_path, template="empty", flash_attn=flash_attn))
         fake_input = torch.ones((batch_size, seq_length), dtype=torch.long, device=chat_model.model.device)
         input_dict = {"input_ids": fake_input, "labels": fake_input.clone()}
         flops, macs, params = get_model_profile(chat_model.model, kwargs=input_dict, print_profile=True, detailed=True)

scripts/cal_lr.py

@@ -4,7 +4,7 @@
 # Inspired by: https://github.com/imoneoi/openchat/blob/master/ochat/training_deepspeed/train.py
 
 import math
-from typing import Optional
+from typing import Literal
 
 import fire
 import torch
@@ -12,10 +12,10 @@ from torch.utils.data import DataLoader
 from tqdm import tqdm
 from transformers import DataCollatorForLanguageModeling, DataCollatorForSeq2Seq
 
-from llmtuner.data import get_dataset
-from llmtuner.extras.constants import IGNORE_INDEX
-from llmtuner.hparams import get_train_args
-from llmtuner.model import load_tokenizer
+from llamafactory.data import get_dataset
+from llamafactory.extras.constants import IGNORE_INDEX
+from llamafactory.hparams import get_train_args
+from llamafactory.model import load_tokenizer
 
 
 BASE_LR = 3e-4  # 1.5e-4 for 30B-70B models
@@ -25,12 +25,12 @@ BASE_BS = 4_000_000  # from llama paper
 def calculate_lr(
     model_name_or_path: str,
     batch_size: int,  # total batch size, namely (batch size * gradient accumulation * world size)
-    stage: Optional[str] = "sft",
-    dataset: Optional[str] = "alpaca_en",
-    dataset_dir: Optional[str] = "data",
-    template: Optional[str] = "default",
-    cutoff_len: Optional[int] = 1024,  # i.e. maximum input length during training
-    is_mistral: Optional[bool] = False,  # mistral model uses a smaller learning rate,
+    stage: Literal["pt", "sft"] = "sft",
+    dataset: str = "alpaca_en",
+    dataset_dir: str = "data",
+    template: str = "default",
+    cutoff_len: int = 1024,  # i.e. maximum input length during training
+    is_mistral: bool = False,  # mistral model uses a smaller learning rate,
 ):
     model_args, data_args, training_args, _, _ = get_train_args(
         dict(
@@ -44,8 +44,9 @@ def calculate_lr(
             overwrite_cache=True,
         )
     )
-    tokenizer = load_tokenizer(model_args)
-    trainset = get_dataset(tokenizer, model_args, data_args, training_args, stage)
+    tokenizer_module = load_tokenizer(model_args)
+    tokenizer = tokenizer_module["tokenizer"]
+    trainset = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
     if stage == "pt":
         data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
     elif stage == "sft":
@@ -53,9 +54,7 @@ def calculate_lr(
     else:
         raise NotImplementedError
 
-    dataloader = DataLoader(
-        dataset=trainset, batch_size=batch_size, shuffle=True, collate_fn=data_collator, pin_memory=True
-    )
+    dataloader = DataLoader(trainset, batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
     valid_tokens, total_tokens = 0, 0
     for batch in tqdm(dataloader):
         valid_tokens += torch.sum(batch["labels"] != IGNORE_INDEX).item()

scripts/cal_ppl.py

@@ -0,0 +1,116 @@
+# coding=utf-8
+# Calculates the ppl on the dataset of the pre-trained models.
+# Usage: python cal_ppl.py --model_name_or_path path_to_model --save_name ppl.json
+
+import json
+from dataclasses import dataclass
+from typing import Any, Dict, Literal, Optional, Sequence
+
+import fire
+import torch
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from transformers import DataCollatorForLanguageModeling, DataCollatorForSeq2Seq
+
+from llamafactory.data import get_dataset
+from llamafactory.extras.constants import IGNORE_INDEX
+from llamafactory.hparams import get_train_args
+from llamafactory.model import load_model, load_tokenizer
+
+
+@dataclass
+class PairwiseDataCollatorWithPadding(DataCollatorForSeq2Seq):
+    r"""
+    Data collator for pairwise data.
+    """
+
+    train_on_prompt: bool = False
+
+    def __call__(self, features: Sequence[Dict[str, Any]]) -> Dict[str, torch.Tensor]:
+        r"""
+        Pads batched data to the longest sequence in the batch.
+
+        We generate 2 * n examples where the first n examples represent chosen examples and
+        the last n examples represent rejected examples.
+        """
+        chosen_features = []
+        for feature in features:
+            prompt_len, answer_len = len(feature["prompt_ids"]), len(feature["chosen_ids"])
+            input_ids = feature["prompt_ids"] + feature["chosen_ids"]
+            attention_mask = [1] * (prompt_len + answer_len)
+            labels = input_ids if self.train_on_prompt else [IGNORE_INDEX] * prompt_len + feature["chosen_ids"]
+            chosen_features.append({"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels})
+
+        return super().__call__(chosen_features)
+
+
+def cal_ppl(
+    model_name_or_path: str,
+    save_name: str,
+    batch_size: int = 4,
+    stage: Literal["pt", "sft", "rm"] = "sft",
+    dataset: str = "alpaca_en",
+    dataset_dir: str = "data",
+    template: str = "default",
+    cutoff_len: int = 1024,
+    max_samples: Optional[int] = None,
+    train_on_prompt: bool = False,
+):
+    model_args, data_args, training_args, finetuning_args, _ = get_train_args(
+        dict(
+            stage=stage,
+            model_name_or_path=model_name_or_path,
+            dataset=dataset,
+            dataset_dir=dataset_dir,
+            template=template,
+            cutoff_len=cutoff_len,
+            max_samples=max_samples,
+            train_on_prompt=train_on_prompt,
+            output_dir="dummy_dir",
+            overwrite_cache=True,
+        )
+    )
+    tokenizer_module = load_tokenizer(model_args)
+    tokenizer = tokenizer_module["tokenizer"]
+    trainset = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
+    model = load_model(tokenizer, model_args, finetuning_args, is_trainable=False)
+    if stage == "pt":
+        data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+    elif stage == "sft":
+        data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, label_pad_token_id=IGNORE_INDEX)
+    elif stage == "rm":
+        data_collator = PairwiseDataCollatorWithPadding(
+            tokenizer=tokenizer, label_pad_token_id=IGNORE_INDEX, train_on_prompt=train_on_prompt
+        )
+    else:
+        raise NotImplementedError
+
+    dataloader = DataLoader(trainset, batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
+    criterion = torch.nn.CrossEntropyLoss(reduction="none")
+    total_ppl = 0
+    perplexities = []
+    batch: Dict[str, "torch.Tensor"]
+    with torch.no_grad():
+        for batch in tqdm(dataloader):
+            batch = batch.to(model.device)
+            outputs = model(**batch)
+            shift_logits: "torch.Tensor" = outputs["logits"][..., :-1, :]
+            shift_labels: "torch.Tensor" = batch["labels"][..., 1:]
+            loss_mask = shift_labels != IGNORE_INDEX
+            flatten_logits = shift_logits.contiguous().view(shift_labels.size(0) * shift_labels.size(1), -1)
+            flatten_labels = shift_labels.contiguous().view(-1)
+            token_logps: "torch.Tensor" = criterion(flatten_logits, flatten_labels)
+            token_logps = token_logps.contiguous().view(shift_logits.size(0), -1)
+            sentence_logps = (token_logps * loss_mask).sum(-1) / loss_mask.sum(-1)
+            total_ppl += sentence_logps.exp().sum().item()
+            perplexities.extend(sentence_logps.exp().tolist())
+
+    with open(save_name, "w", encoding="utf-8") as f:
+        json.dump(perplexities, f, indent=2)
+
+    print("Average perplexity is {:.2f}".format(total_ppl / len(perplexities)))
+    print("Perplexities have been saved at {}.".format(save_name))
+
+
+if __name__ == "__main__":
+    fire.Fire(cal_ppl)

scripts/length_cdf.py

@@ -3,22 +3,21 @@
 # Usage: python length_cdf.py --model_name_or_path path_to_model --dataset alpaca_en --template default
 
 from collections import defaultdict
-from typing import Optional
 
 import fire
 from tqdm import tqdm
 
-from llmtuner.data import get_dataset
-from llmtuner.hparams import get_train_args
-from llmtuner.model import load_tokenizer
+from llamafactory.data import get_dataset
+from llamafactory.hparams import get_train_args
+from llamafactory.model import load_tokenizer
 
 
 def length_cdf(
     model_name_or_path: str,
-    dataset: Optional[str] = "alpaca_en",
-    dataset_dir: Optional[str] = "data",
-    template: Optional[str] = "default",
-    interval: Optional[int] = 1000,
+    dataset: str = "alpaca_en",
+    dataset_dir: str = "data",
+    template: str = "default",
+    interval: int = 1000,
 ):
     model_args, data_args, training_args, _, _ = get_train_args(
         dict(
@@ -32,8 +31,8 @@ def length_cdf(
             overwrite_cache=True,
         )
     )
-    tokenizer = load_tokenizer(model_args)
-    trainset = get_dataset(tokenizer, model_args, data_args, training_args, stage="sft")
+    tokenizer_module = load_tokenizer(model_args)
+    trainset = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
     total_num = len(trainset)
     length_dict = defaultdict(int)
     for sample in tqdm(trainset["input_ids"]):