release v0.7.1

Former-commit-id: a4f8adb021b6218d624303b51cd5e93ffa3111a1

Dockerfile

@@ -11,4 +11,4 @@ RUN pip install -e .[deepspeed,metrics,bitsandbytes,qwen]
 VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
 EXPOSE 7860
 
-CMD [ "python", "src/train_web.py" ]
+CMD [ "llamafactory-cli", "webui" ]

README.md

@@ -5,7 +5,7 @@
 [![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)
+[![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)
@@ -13,6 +13,8 @@
 [![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).
 
 \[ English | [中文](README_zh.md) \]
@@ -43,8 +45,8 @@ 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 and ORPO.
 - **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 +70,61 @@ 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.
+[24/05/14] We supported training and inference on the Ascend NPU devices. Check [installation](#installation) section for details.
 
-[24/04/19] We supported **Meta Llama 3** model series.
+[24/05/13] We supported fine-tuning the **Yi-1.5** series 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).
+[24/04/26] We supported fine-tuning the **LLaVA-1.5** multimodal LLMs. 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.
+[24/04/22] 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`.
 
-[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.
 
@@ -128,40 +136,45 @@ 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  |
+| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | 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    |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)             | 7B/13B                           | q_proj,v_proj     | vicuna    |
 | [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B                    | q_proj,v_proj     | mistral   |
-| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                       | att_proj          | olmo      |
+| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                            | q_proj,v_proj     | -         |
 | [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                        | q_proj,v_proj     | -         |
+| [Phi-3](https://huggingface.co/microsoft)                | 3.8B                             | qkv_proj          | phi       |
 | [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      |
+| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | 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        |
+| [Yi (1/1.5)](https://huggingface.co/01-ai)               | 6B/9B/34B                        | q_proj,v_proj     | yi        |
+| [Yi-VL](https://huggingface.co/01-ai)                    | 6B/34B                           | q_proj,v_proj     | yi_vl     |
 | [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                      | q_proj,v_proj     | yuan      |
 
 > [!NOTE]
-> **Default module** is used for the `--lora_target` argument, you can use `--lora_target all` to specify all the available modules.
+> **Default module** is used for the `--lora_target` argument, you can use `--lora_target all` to specify all the available modules for better convergence.
 >
-> 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.
+> 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.
+>
+> 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.
 
@@ -199,8 +212,8 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
 - [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
 - [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)
+- [Identity (en&zh)](data/identity.json)
+- [Open Assistant (zh)](https://huggingface.co/datasets/OpenAssistant/oasst1)
 - [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection)
 - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
 - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
@@ -232,6 +245,7 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 - [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)
+- [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)
@@ -247,11 +261,11 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ
 <details><summary>Preference datasets</summary>
 
 - [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)
+- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [Open Assistant (zh)](https://huggingface.co/datasets/OpenAssistant/oasst1)
 - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
 
 </details>
@@ -269,57 +283,55 @@ huggingface-cli login
 | ------------ | ------- | --------- |
 | 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    |
+| transformers | 4.37.2  | 4.40.1    |
+| datasets     | 2.14.3  | 2.19.1    |
+| accelerate   | 0.27.2  | 0.30.0    |
 | peft         | 0.9.0   | 0.10.0    |
-| trl          | 0.8.1   | 0.8.1     |
+| trl          | 0.8.1   | 0.8.6     |
 
 | 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         | 0.4.0   | 0.4.2     |
+| flash-attn   | 2.3.0   | 2.5.8     |
 
 ### 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
 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, 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 +341,77 @@ 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>
+
+To utilize Ascend NPU devices for (distributed) training and inference, you need to install the **[torch-npu](https://gitee.com/ascend/pytorch)** library and the **[Ascend CANN Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**.
+
+| Requirement  | Minimum | Recommend |
+| ------------ | ------- | --------- |
+| CANN         | 8.0.RC1 | 8.0.RC1   |
+| torch        | 2.2.0   | 2.2.0     |
+| torch-npu    | 2.2.0   | 2.2.0     |
+| deepspeed    | 0.13.2  | 0.13.2    |
+
+Docker image:
+
+- 32GB: [Download page](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html)
+- 64GB: Coming soon
+
+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))
 
 > [!IMPORTANT]
-> LLaMA Board GUI only supports training on a single GPU, please use [CLI](#command-line-interface) for distributed training.
+> LLaMA Board GUI only supports training on a single GPU.
 
 #### 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><summary>For Alibaba Cloud PAI or AutoDL users</summary>
+
+If you encountered display problems in LLaMA Board on Alibaba Cloud PAI, try using the following command to set environment variables before starting LLaMA Board:
+
+```bash
+export GRADIO_SERVER_PORT=7860 GRADIO_ROOT_PATH=/${JUPYTER_NAME}/proxy/7860/
+```
+
+If you are using AutoDL, please install a specific version of Gradio:
+
+```bash
+pip install gradio==4.10.0
+```
+
+</details>
+
 #### Use Docker
 
 ```bash
@@ -371,23 +441,13 @@ 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
+### Download from ModelScope Hub
 
 If you have trouble with downloading models and datasets from Hugging Face, you can use ModelScope.
 
@@ -395,7 +455,7 @@ 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`.
 
 ## Projects using LLaMA Factory
 
@@ -424,6 +484,7 @@ 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 +492,21 @@ 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. **[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 +514,7 @@ 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) / [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

@@ -5,13 +5,15 @@
 [![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)
+[![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)
 [![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)
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?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 +25,7 @@ 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
 - **本地机器**：请见[如何使用](#如何使用)
 
 ## 目录
@@ -43,8 +45,8 @@ 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 训练和 ORPO 训练。
 - **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 +70,61 @@ 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`。
+[24/05/14] 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。
 
-[24/04/19] 我们支持了 **Meta Llama 3** 系列模型。
+[24/05/13] 我们支持了 Yi-1.5 系列模型的微调。
 
-[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)。
+[24/04/26] 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)。
 
 <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`。
+[24/04/22] 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` 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)）。
 
@@ -128,40 +136,45 @@ 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  |
+| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | 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    |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)             | 7B/13B                           | q_proj,v_proj     | vicuna    |
 | [Mistral/Mixtral](https://huggingface.co/mistralai)      | 7B/8x7B/8x22B                    | q_proj,v_proj     | mistral   |
-| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                       | att_proj          | olmo      |
+| [OLMo](https://huggingface.co/allenai)                   | 1B/7B                            | q_proj,v_proj     | -         |
 | [Phi-1.5/2](https://huggingface.co/microsoft)            | 1.3B/2.7B                        | q_proj,v_proj     | -         |
+| [Phi-3](https://huggingface.co/microsoft)                | 3.8B                             | qkv_proj          | phi       |
 | [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      |
+| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)        | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | 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        |
+| [Yi (1/1.5)](https://huggingface.co/01-ai)               | 6B/9B/34B                        | q_proj,v_proj     | yi        |
+| [Yi-VL](https://huggingface.co/01-ai)                    | 6B/34B                           | q_proj,v_proj     | yi_vl     |
 | [Yuan](https://huggingface.co/IEITYuan)                  | 2B/51B/102B                      | q_proj,v_proj     | 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。
+> **默认模块**应作为 `--lora_target` 参数的默认值，可使用 `--lora_target all` 参数指定全部模块以取得更好的效果。
 >
-> 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**。
+> 对于所有“基座”（Base）模型，`--template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
+>
+> 请务必在训练和推理时使用**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)。
 
@@ -199,8 +212,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
 - [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
 - [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)
+- [Identity (en&zh)](data/identity.json)
+- [Open Assistant (zh)](https://huggingface.co/datasets/OpenAssistant/oasst1)
 - [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection)
 - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
 - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
@@ -232,6 +245,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [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)
+- [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)
@@ -247,11 +261,11 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 <details><summary>偏好数据集</summary>
 
 - [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)
+- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [Open Assistant (zh)](https://huggingface.co/datasets/OpenAssistant/oasst1)
 - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
 
 </details>
@@ -269,53 +283,51 @@ huggingface-cli login
 | ------------ | ------- | --------- |
 | 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    |
+| transformers | 4.37.2  | 4.40.1    |
+| datasets     | 2.14.3  | 2.19.1    |
+| accelerate   | 0.27.2  | 0.30.0    |
 | peft         | 0.9.0   | 0.10.0    |
-| trl          | 0.8.1   | 0.8.1     |
+| trl          | 0.8.1   | 0.8.6     |
 
 | 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         | 0.4.0   | 0.4.2     |
+| flash-attn   | 2.3.0   | 2.5.8     |
 
 ### 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
 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、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>
 
@@ -329,19 +341,77 @@ 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>
+
+如果使用昇腾 NPU 设备进行（分布式）训练或推理，需要安装 **[torch-npu](https://gitee.com/ascend/pytorch)** 库和 **[Ascend CANN Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**。
+
+| 依赖项       | 至少     | 推荐      |
+| ------------ | ------- | --------- |
+| CANN         | 8.0.RC1 | 8.0.RC1   |
+| torch        | 2.2.0   | 2.2.0     |
+| torch-npu    | 2.2.0   | 2.2.0     |
+| 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：敬请期待
+
+请记得使用 `ASCEND_RT_VISIBLE_DEVICES` 而非 `CUDA_VISIBLE_DEVICES` 来指定您使用的设备。
+
+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）
 
 > [!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。
+> LLaMA Board 可视化界面目前仅支持单 GPU 训练。
 
 #### 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
 ```
 
+<details><summary>阿里云 PAI 和 AutoDL 用户指南</summary>
+
+如果您在阿里云 PAI 上使用 LLaMA Board 时遇到显示问题，请尝试在启动前使用以下命令设置环境变量：
+
+```bash
+export GRADIO_SERVER_PORT=7860 GRADIO_ROOT_PATH=/${JUPYTER_NAME}/proxy/7860/
+```
+
+如果您正在使用 AutoDL，请安装下述 Gradio 版本：
+
+```bash
+pip install gradio==4.10.0
+```
+
+</details>
+
 #### 使用 Docker
 
 ```bash
@@ -371,23 +441,13 @@ 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
+### 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 +455,7 @@ 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`。
 
 ## 使用了 LLaMA Factory 的项目
 
@@ -424,6 +484,7 @@ 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 +492,21 @@ 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. **[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 +514,7 @@ 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) / [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

@@ -1,4 +1,4 @@
-If you are using a custom dataset, please provide your dataset definition in the following format in `dataset_info.json`.
+If you are using a custom dataset, please add your **dataset description** to `dataset_info.json` according to the following format. We also provide several examples in the next section.
 
 ```json
 "dataset_name": {
@@ -18,7 +18,8 @@ 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)"
   },
   "tags (optional, used for the sharegpt format)": {
     "role_tag": "the key in the message represents the identity. (default: from)",
@@ -32,7 +33,7 @@ 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`.
+After that, you can load the custom dataset by specifying `--dataset dataset_name`.
 
 ----
 
@@ -53,10 +54,11 @@ Currently we support dataset in **alpaca** or **sharegpt** format, the dataset i
 ]
 ```
 
-Regarding the above dataset, the `columns` in `dataset_info.json` should be:
+Regarding the above dataset, the description in `dataset_info.json` should be:
 
 ```json
 "dataset_name": {
+  "file_name": "data.json",
   "columns": {
     "prompt": "instruction",
     "query": "input",
@@ -69,28 +71,60 @@ 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.
 
-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**.
+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** in supervised fine-tuning.
 
-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:
+For the **pre-training datasets**, only the `prompt` column will be used for training, for example:
 
 ```json
-{
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+Regarding the above dataset, the description in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
+}
+```
+
+For the **preference datasets**, the `response` column should be a string list whose length is 2, with the preferred answers appearing first, for example:
+
+```json
+[
+  {
     "instruction": "user instruction",
     "input": "user input",
     "output": [
       "chosen answer",
       "rejected answer"
     ]
+  }
+]
+```
+
+Regarding the above dataset, the description in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+  }
 }
 ```
 
-Remember to set `"ranking": true` for the preference datasets.
-
 ----
 
-The dataset in sharegpt format should follow the below format:
+The dataset in **sharegpt** format should follow the below format:
 
 ```json
 [
@@ -111,10 +145,12 @@ 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 description in `dataset_info.json` should be:
 
 ```json
 "dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
   "columns": {
     "messages": "conversations",
     "system": "system",
@@ -131,4 +167,46 @@ Regarding the above dataset, the `columns` in `dataset_info.json` should be:
 
 where the `messages` column should be a list following the `u/a/u/a/u/a` order.
 
-Pre-training datasets and preference datasets are incompatible with the sharegpt format yet.
+We also supports the dataset in the **openai** format:
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "system prompt (optional)"
+      },
+      {
+        "role": "user",
+        "content": "user instruction"
+      },
+      {
+        "role": "assistant",
+        "content": "model response"
+      }
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the 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"
+  }
+}
+```
+
+Pre-training datasets and preference datasets are **incompatible** with the sharegpt format yet.

data/README_zh.md

@@ -1,4 +1,4 @@
-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。
+如果您使用自定义数据集，请务必按照以下格式在 `dataset_info.json` 文件中添加**数据集描述**。我们在下面也提供了一些例子。
 
 ```json
 "数据集名称": {
@@ -18,7 +18,8 @@
     "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）"
   },
   "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）",
@@ -32,7 +33,7 @@
 }
 ```
 
-添加后可通过指定 `--dataset 数据集名称` 参数使用自定义数据集。
+然后，可通过使用 `--dataset 数据集名称` 参数加载自定义数据集。
 
 ----
 
@@ -53,10 +54,11 @@
 ]
 ```
 
-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` 中的描述应为：
 
 ```json
 "数据集名称": {
+  "file_name": "data.json",
   "columns": {
     "prompt": "instruction",
     "query": "input",
@@ -69,28 +71,60 @@
 
 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。
 
-`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**。
+`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。注意在指令监督学习时，历史消息中的回答**也会被用于训练**。
 
-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：
+对于**预训练数据集**，仅 `prompt` 列中的内容会用于模型训练，例如：
 
 ```json
-{
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的描述应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
+}
+```
+
+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：
+
+```json
+[
+  {
     "instruction": "用户指令",
     "input": "用户输入",
     "output": [
       "优质回答",
       "劣质回答"
     ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的描述应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+  }
 }
 ```
 
-添加偏好数据集需要额外指定 `"ranking": true`。
-
 ----
 
-而 sharegpt 格式的数据集按照以下方式组织：
+而 **sharegpt** 格式的数据集按照以下方式组织：
 
 ```json
 [
@@ -111,10 +145,12 @@
 ]
 ```
 
-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` 中的描述应为：
 
 ```json
 "数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
   "columns": {
     "messages": "conversations",
     "system": "system",
@@ -131,4 +167,46 @@
 
 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。
 
-预训练数据集和偏好数据集尚不支持 sharegpt 格式。
+我们同样支持 **openai** 格式的数据集：
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "系统提示词（选填）"
+      },
+      {
+        "role": "user",
+        "content": "用户指令"
+      },
+      {
+        "role": "assistant",
+        "content": "模型回答"
+      }
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的描述应为：
+
+```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"
+  }
+}
+```
+
+预训练数据集和偏好数据集**尚不支持** sharegpt 格式。

data/oaast_rm.json.REMOVED.git-id

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

data/oaast_sft.json.REMOVED.git-id

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

evaluation/ceval/ceval.py

@@ -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

@@ -136,25 +136,19 @@ 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"),
                 },
             ),
         ]

examples/README.md

@@ -1,48 +1,229 @@
 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 Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_dpo.yaml
+```
+
+#### ORPO Training
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_orpo.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 with Accelerate on Single Node
+
+```bash
+bash examples/lora_multi_gpu/single_node.sh
+```
+
+#### Supervised Fine-Tuning with Accelerate on Multiple Nodes
+
+```bash
+bash examples/lora_multi_gpu/multi_node.sh
+```
+
+#### Supervised Fine-Tuning with DeepSpeed ZeRO-3 (Weight Sharding)
+
+```bash
+bash examples/lora_multi_gpu/ds_zero3.sh
+```
+
+### LoRA Fine-Tuning on Multiple NPUs
+
+#### Supervised Fine-Tuning with DeepSpeed ZeRO-0
+
+```bash
+bash examples/lora_multi_npu/ds_zero0.sh
+```
+
+### Full-Parameter Fine-Tuning on Multiple GPUs
+
+#### Supervised Fine-Tuning with Accelerate on Single Node
+
+```bash
+bash examples/full_multi_gpu/single_node.sh
+```
+
+#### Supervised Fine-Tuning with Accelerate on Multiple Nodes
+
+```bash
+bash examples/full_multi_gpu/multi_node.sh
+```
+
+#### Batch Predicting and Computing BLEU and ROUGE Scores
+
+```bash
+bash examples/full_multi_gpu/predict.sh
+```
+
+### 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 CLI
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### Use Web UI
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### Launch OpenAI-style API
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli api examples/merge_lora/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 +1,229 @@
 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 训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_dpo.yaml
+```
+
+#### ORPO 训练
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_orpo.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
+
+#### 使用 Accelerate 进行单节点训练
+
+```bash
+bash examples/lora_multi_gpu/single_node.sh
+```
+
+#### 使用 Accelerate 进行多节点训练
+
+```bash
+bash examples/lora_multi_gpu/multi_node.sh
+```
+
+#### 使用 DeepSpeed ZeRO-3 平均分配显存
+
+```bash
+bash examples/lora_multi_gpu/ds_zero3.sh
+```
+
+### 多 NPU LoRA 微调
+
+#### 使用 DeepSpeed ZeRO-0 训练
+
+```bash
+bash examples/lora_multi_npu/ds_zero0.sh
+```
+
+### 多 GPU 全参数微调
+
+#### 使用 DeepSpeed 进行单节点训练
+
+```bash
+bash examples/full_multi_gpu/single_node.sh
+```
+
+#### 使用 DeepSpeed 进行多节点训练
+
+```bash
+bash examples/full_multi_gpu/multi_node.sh
+```
+
+#### 批量预测并计算 BLEU 和 ROUGE 分数
+
+```bash
+bash examples/full_multi_gpu/predict.sh
+```
+
+### 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
+
+#### 使用命令行接口
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### 使用浏览器界面
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat examples/merge_lora/llama3_lora_sft.yaml
+```
+
+#### 启动 OpenAI 风格 API
+
+```bash
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli api examples/merge_lora/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/master_config.yaml

@@ -9,7 +9,7 @@ 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
+num_processes: 8 # the number of GPUs in all nodes
 rdzv_backend: static
 same_network: true
 tpu_env: []

examples/accelerate/slave_config.yaml

@@ -9,7 +9,7 @@ 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
+num_processes: 8 # the number of GPUs in all nodes
 rdzv_backend: static
 same_network: true
 tpu_env: []

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: descending
+badam_switch_interval: 50
+badam_verbose: 2
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+pure_bf16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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 +1,10 @@
+#!/bin/bash
+# DO NOT use GPTQ/AWQ model in FSDP+QLoRA
+
+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 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_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+pure_bf16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+loraplus_lr_ratio: 16.0
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+pure_bf16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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_gpt4_en
+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_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/full_multi_gpu/multi_node.sh

@@ -1,38 +1,15 @@
 #!/bin/bash
 
-python -m torch.distributed.run \
+NPROC_PER_NODE=4
+NNODES=2
+RANK=0
+MASTER_ADDR=192.168.0.1
+MASTER_PORT=29500
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun \
     --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
+    src/train.py examples/full_multi_gpu/llama3_full_sft.yaml

examples/full_multi_gpu/predict.sh

@@ -1,18 +1,5 @@
 #!/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
+CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
+    --config_file examples/accelerate/single_config.yaml \
+    src/train.py examples/full_multi_gpu/llama3_full_predict.yaml

examples/full_multi_gpu/single_node.sh

@@ -1,32 +1,15 @@
 #!/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
+NPROC_PER_NODE=4
+NNODES=1
+RANK=0
+MASTER_ADDR=127.0.0.1
+MASTER_PORT=29500
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun \
+    --nproc_per_node $NPROC_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT \
+    src/train.py examples/full_multi_gpu/llama3_full_sft.yaml

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/ds_zero3.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+NPROC_PER_NODE=4
+NNODES=1
+RANK=0
+MASTER_ADDR=127.0.0.1
+MASTER_PORT=29500
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun \
+    --nproc_per_node $NPROC_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT \
+    src/train.py examples/lora_multi_gpu/llama3_lora_sft_ds.yaml

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: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

examples/lora_multi_gpu/multi_node.sh

@@ -1,35 +1,6 @@
 #!/bin/bash
+# also launch it on slave machine using slave_config.yaml
 
 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
+    --config_file examples/accelerate/master_config.yaml \
+    src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml

examples/lora_multi_gpu/single_node.sh

@@ -1,35 +1,5 @@
 #!/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
+CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
+    --config_file examples/accelerate/single_config.yaml \
+    src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml

examples/lora_multi_npu/ds_zero0.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+NPROC_PER_NODE=4
+NNODES=1
+RANK=0
+MASTER_ADDR=127.0.0.1
+MASTER_PORT=29500
+
+ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 torchrun \
+    --nproc_per_node $NPROC_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT \
+    src/train.py examples/lora_multi_npu/llama3_lora_sft_ds.yaml

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: q_proj,v_proj
+
+# ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z0_config.json
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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 +1,39 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+# method
+stage: dpo
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+dpo_ftx: 1.0
+
+# dataset
+dataset: orca_rlhf
+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: 0.00001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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_orpo.yaml

@@ -0,0 +1,38 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+
+# method
+stage: orpo
+do_train: true
+finetuning_type: lora
+lora_target: q_proj,v_proj
+
+# dataset
+dataset: orca_rlhf
+template: llama3
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+# output
+output_dir: saves/llama3-8b/lora/orpo
+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: 0.00001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.00001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 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_gpt4_en
+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: q_proj,v_proj
+
+# 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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: orca_rlhf
+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: 0.00001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: q_proj,v_proj
+
+# 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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_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: q_proj,v_proj
+
+# dataset
+dataset: identity,alpaca_gpt4_en
+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: 0.0001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 0.1
+fp16: true
+
+# eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+evaluation_strategy: steps
+eval_steps: 500

requirements.txt

@@ -1,4 +1,3 @@
-torch>=1.13.1
 transformers>=4.37.2
 datasets>=2.14.3
 accelerate>=0.27.2
@@ -13,5 +12,7 @@ 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 llmtuner.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
@@ -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 llmtuner.data import get_dataset
+from llmtuner.extras.constants import IGNORE_INDEX
+from llmtuner.hparams import get_train_args
+from llmtuner.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

@@ -3,7 +3,6 @@
 # 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
@@ -15,10 +14,10 @@ from llmtuner.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"]):

scripts/llama_pro.py

@@ -1,5 +1,5 @@
 # coding=utf-8
-# Performs block expansion for LLaMA, Mistral or Qwen1.5 models.
+# Performs block expansion for LLaMA, Mistral, Qwen1.5 or Yi models.
 # Usage: python llama_pro.py --model_name_or_path meta-llama/Llama-2-7b-hf --output_dir llama2_pro --num_expand 8
 # Inspired by: https://github.com/TencentARC/LLaMA-Pro/blob/main/scripts/block_expansion.py
 
@@ -106,8 +106,7 @@ def block_expansion(
     print("Fine-tune this model with:")
     print("  --model_name_or_path {} \\".format(output_dir))
     print("  --finetuning_type freeze \\")
-    print("  --name_module_trainable all \\")
-    print("  --num_layer_trainable {} \\".format(num_expand))
+    print("  --freeze_trainable_layers {} \\".format(num_expand))
     print("  --use_llama_pro")
 
 

setup.py

@@ -5,9 +5,9 @@ from setuptools import find_packages, setup
 
 
 def get_version():
-    with open(os.path.join("src", "llmtuner", "__init__.py"), "r", encoding="utf-8") as f:
+    with open(os.path.join("src", "llmtuner", "cli.py"), "r", encoding="utf-8") as f:
         file_content = f.read()
-        pattern = r"{0}\W*=\W*\"([^\"]+)\"".format("__version__")
+        pattern = r"{}\W*=\W*\"([^\"]+)\"".format("VERSION")
         (version,) = re.findall(pattern, file_content)
         return version
 
@@ -20,13 +20,13 @@ def get_requires():
 
 
 extra_require = {
-    "deepspeed": ["deepspeed>=0.10.0"],
+    "torch": ["torch>=1.13.1"],
     "metrics": ["nltk", "jieba", "rouge-chinese"],
-    "unsloth": ["torch==2.2.0", "unsloth[cu121-ampere-torch220]"],
+    "deepspeed": ["deepspeed>=0.10.0,<=0.14.0"],
+    "bitsandbytes": ["bitsandbytes>=0.39.0"],
+    "vllm": ["vllm>=0.4.0"],
     "galore": ["galore-torch"],
     "badam": ["badam"],
-    "vllm": ["vllm>=0.3.3"],
-    "bitsandbytes": ["bitsandbytes>=0.39.0"],
     "gptq": ["optimum>=1.16.0", "auto-gptq>=0.5.0"],
     "awq": ["autoawq"],
     "aqlm": ["aqlm[gpu]>=1.1.0"],
@@ -53,6 +53,7 @@ def main():
         python_requires=">=3.8.0",
         install_requires=get_requires(),
         extras_require=extra_require,
+        entry_points={"console_scripts": ["llamafactory-cli = llmtuner.cli:main"]},
         classifiers=[
             "Development Status :: 4 - Beta",
             "Intended Audience :: Developers",

src/api.py

@@ -0,0 +1,19 @@
+import os
+
+import uvicorn
+
+from llmtuner.api.app import create_app
+from llmtuner.chat import ChatModel
+
+
+def main():
+    chat_model = ChatModel()
+    app = create_app(chat_model)
+    api_host = os.environ.get("API_HOST", "0.0.0.0")
+    api_port = int(os.environ.get("API_PORT", "8000"))
+    print("Visit http://localhost:{}/docs for API document.".format(api_port))
+    uvicorn.run(app, host=api_host, port=api_port)
+
+
+if __name__ == "__main__":
+    main()

src/api_demo.py

@@ -1,16 +0,0 @@
-import os
-
-import uvicorn
-
-from llmtuner import ChatModel, create_app
-
-
-def main():
-    chat_model = ChatModel()
-    app = create_app(chat_model)
-    print("Visit http://localhost:{}/docs for API document.".format(os.environ.get("API_PORT", 8000)))
-    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)
-
-
-if __name__ == "__main__":
-    main()

src/cli_demo.py

@@ -1,49 +0,0 @@
-from llmtuner import ChatModel
-from llmtuner.extras.misc import torch_gc
-
-
-try:
-    import platform
-
-    if platform.system() != "Windows":
-        import readline  # noqa: F401
-except ImportError:
-    print("Install `readline` for a better experience.")
-
-
-def main():
-    chat_model = ChatModel()
-    messages = []
-    print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.")
-
-    while True:
-        try:
-            query = input("\nUser: ")
-        except UnicodeDecodeError:
-            print("Detected decoding error at the inputs, please set the terminal encoding to utf-8.")
-            continue
-        except Exception:
-            raise
-
-        if query.strip() == "exit":
-            break
-
-        if query.strip() == "clear":
-            messages = []
-            torch_gc()
-            print("History has been removed.")
-            continue
-
-        messages.append({"role": "user", "content": query})
-        print("Assistant: ", end="", flush=True)
-
-        response = ""
-        for new_text in chat_model.stream_chat(messages):
-            print(new_text, end="", flush=True)
-            response += new_text
-        print()
-        messages.append({"role": "assistant", "content": response})
-
-
-if __name__ == "__main__":
-    main()

src/evaluate.py

@@ -1,9 +0,0 @@
-from llmtuner import Evaluator
-
-
-def main():
-    Evaluator().eval()
-
-
-if __name__ == "__main__":
-    main()

src/export_model.py

@@ -1,9 +0,0 @@
-from llmtuner import export_model
-
-
-def main():
-    export_model()
-
-
-if __name__ == "__main__":
-    main()

src/llmtuner/__init__.py

@@ -1,11 +1,6 @@
 # Level: api, webui > chat, eval, train > data, model > extras, hparams
 
-from .api import create_app
-from .chat import ChatModel
-from .eval import Evaluator
-from .train import export_model, run_exp
-from .webui import create_ui, create_web_demo
+from .cli import VERSION
 
 
-__version__ = "0.6.3"
-__all__ = ["create_app", "ChatModel", "Evaluator", "export_model", "run_exp", "create_ui", "create_web_demo"]
+__version__ = VERSION

src/llmtuner/api/__init__.py

@@ -1,4 +0,0 @@
-from .app import create_app
-
-
-__all__ = ["create_app"]

src/llmtuner/api/app.py

@@ -1,36 +1,31 @@
-import json
 import os
 from contextlib import asynccontextmanager
-from typing import Any, Dict, Sequence
+from typing import Optional
 
-from pydantic import BaseModel
+from typing_extensions import Annotated
 
 from ..chat import ChatModel
-from ..data import Role as DataRole
 from ..extras.misc import torch_gc
-from ..extras.packages import is_fastapi_availble, is_starlette_available, is_uvicorn_available
+from ..extras.packages import is_fastapi_available, is_starlette_available, is_uvicorn_available
+from .chat import (
+    create_chat_completion_response,
+    create_score_evaluation_response,
+    create_stream_chat_completion_response,
+)
 from .protocol import (
-    ChatCompletionMessage,
     ChatCompletionRequest,
     ChatCompletionResponse,
-    ChatCompletionResponseChoice,
-    ChatCompletionResponseStreamChoice,
-    ChatCompletionResponseUsage,
-    ChatCompletionStreamResponse,
-    Finish,
-    Function,
-    FunctionCall,
     ModelCard,
     ModelList,
-    Role,
     ScoreEvaluationRequest,
     ScoreEvaluationResponse,
 )
 
 
-if is_fastapi_availble():
-    from fastapi import FastAPI, HTTPException, status
+if is_fastapi_available():
+    from fastapi import Depends, FastAPI, HTTPException, status
     from fastapi.middleware.cors import CORSMiddleware
+    from fastapi.security.http import HTTPAuthorizationCredentials, HTTPBearer
 
 
 if is_starlette_available():
@@ -47,23 +42,8 @@ async def lifespan(app: "FastAPI"):  # collects GPU memory
     torch_gc()
 
 
-def dictify(data: "BaseModel") -> Dict[str, Any]:
-    try:  # pydantic v2
-        return data.model_dump(exclude_unset=True)
-    except AttributeError:  # pydantic v1
-        return data.dict(exclude_unset=True)
-
-
-def jsonify(data: "BaseModel") -> str:
-    try:  # pydantic v2
-        return json.dumps(data.model_dump(exclude_unset=True), ensure_ascii=False)
-    except AttributeError:  # pydantic v1
-        return data.json(exclude_unset=True, ensure_ascii=False)
-
-
 def create_app(chat_model: "ChatModel") -> "FastAPI":
     app = FastAPI(lifespan=lifespan)
-
     app.add_middleware(
         CORSMiddleware,
         allow_origins=["*"],
@@ -71,160 +51,58 @@ def create_app(chat_model: "ChatModel") -> "FastAPI":
         allow_methods=["*"],
         allow_headers=["*"],
     )
+    api_key = os.environ.get("API_KEY")
+    security = HTTPBearer(auto_error=False)
 
-    role_mapping = {
-        Role.USER: DataRole.USER.value,
-        Role.ASSISTANT: DataRole.ASSISTANT.value,
-        Role.SYSTEM: DataRole.SYSTEM.value,
-        Role.FUNCTION: DataRole.FUNCTION.value,
-        Role.TOOL: DataRole.OBSERVATION.value,
-    }
+    async def verify_api_key(auth: Annotated[Optional[HTTPAuthorizationCredentials], Depends(security)]):
+        if api_key and (auth is None or auth.credentials != api_key):
+            raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid API key.")
 
-    @app.get("/v1/models", response_model=ModelList)
+    @app.get(
+        "/v1/models",
+        response_model=ModelList,
+        status_code=status.HTTP_200_OK,
+        dependencies=[Depends(verify_api_key)],
+    )
     async def list_models():
         model_card = ModelCard(id="gpt-3.5-turbo")
         return ModelList(data=[model_card])
 
-    @app.post("/v1/chat/completions", response_model=ChatCompletionResponse, status_code=status.HTTP_200_OK)
+    @app.post(
+        "/v1/chat/completions",
+        response_model=ChatCompletionResponse,
+        status_code=status.HTTP_200_OK,
+        dependencies=[Depends(verify_api_key)],
+    )
     async def create_chat_completion(request: ChatCompletionRequest):
         if not chat_model.engine.can_generate:
             raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
 
-        if len(request.messages) == 0:
-            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length")
-
-        if request.messages[0].role == Role.SYSTEM:
-            system = request.messages.pop(0).content
-        else:
-            system = ""
-
-        if len(request.messages) % 2 == 0:
-            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")
-
-        input_messages = []
-        for i, message in enumerate(request.messages):
-            if i % 2 == 0 and message.role not in [Role.USER, Role.TOOL]:
-                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
-            elif i % 2 == 1 and message.role not in [Role.ASSISTANT, Role.FUNCTION]:
-                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
-
-            if message.role == Role.ASSISTANT and isinstance(message.tool_calls, list) and len(message.tool_calls):
-                name = message.tool_calls[0].function.name
-                arguments = message.tool_calls[0].function.arguments
-                content = json.dumps({"name": name, "argument": arguments}, ensure_ascii=False)
-                input_messages.append({"role": role_mapping[Role.FUNCTION], "content": content})
-            else:
-                input_messages.append({"role": role_mapping[message.role], "content": message.content})
-
-        tool_list = request.tools
-        if isinstance(tool_list, list) and len(tool_list):
-            try:
-                tools = json.dumps([dictify(tool.function) for tool in tool_list], ensure_ascii=False)
-            except Exception:
-                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid tools")
-        else:
-            tools = ""
-
         if request.stream:
-            if tools:
-                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Cannot stream function calls.")
-
-            generate = stream_chat_completion(input_messages, system, tools, request)
+            generate = create_stream_chat_completion_response(request, chat_model)
             return EventSourceResponse(generate, media_type="text/event-stream")
-
-        responses = await chat_model.achat(
-            input_messages,
-            system,
-            tools,
-            do_sample=request.do_sample,
-            temperature=request.temperature,
-            top_p=request.top_p,
-            max_new_tokens=request.max_tokens,
-            num_return_sequences=request.n,
-        )
-
-        prompt_length, response_length = 0, 0
-        choices = []
-        for i, response in enumerate(responses):
-            if tools:
-                result = chat_model.engine.template.format_tools.extract(response.response_text)
         else:
-                result = response.response_text
+            return await create_chat_completion_response(request, chat_model)
 
-            if isinstance(result, tuple):
-                name, arguments = result
-                function = Function(name=name, arguments=arguments)
-                response_message = ChatCompletionMessage(
-                    role=Role.ASSISTANT, tool_calls=[FunctionCall(function=function)]
+    @app.post(
+        "/v1/score/evaluation",
+        response_model=ScoreEvaluationResponse,
+        status_code=status.HTTP_200_OK,
+        dependencies=[Depends(verify_api_key)],
     )
-                finish_reason = Finish.TOOL
-            else:
-                response_message = ChatCompletionMessage(role=Role.ASSISTANT, content=result)
-                finish_reason = Finish.STOP if response.finish_reason == "stop" else Finish.LENGTH
-
-            choices.append(
-                ChatCompletionResponseChoice(index=i, message=response_message, finish_reason=finish_reason)
-            )
-            prompt_length = response.prompt_length
-            response_length += response.response_length
-
-        usage = ChatCompletionResponseUsage(
-            prompt_tokens=prompt_length,
-            completion_tokens=response_length,
-            total_tokens=prompt_length + response_length,
-        )
-
-        return ChatCompletionResponse(model=request.model, choices=choices, usage=usage)
-
-    async def stream_chat_completion(
-        messages: Sequence[Dict[str, str]], system: str, tools: str, request: ChatCompletionRequest
-    ):
-        choice_data = ChatCompletionResponseStreamChoice(
-            index=0, delta=ChatCompletionMessage(role=Role.ASSISTANT, content=""), finish_reason=None
-        )
-        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
-        yield jsonify(chunk)
-
-        async for new_token in chat_model.astream_chat(
-            messages,
-            system,
-            tools,
-            do_sample=request.do_sample,
-            temperature=request.temperature,
-            top_p=request.top_p,
-            max_new_tokens=request.max_tokens,
-        ):
-            if len(new_token) == 0:
-                continue
-
-            choice_data = ChatCompletionResponseStreamChoice(
-                index=0, delta=ChatCompletionMessage(content=new_token), finish_reason=None
-            )
-            chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
-            yield jsonify(chunk)
-
-        choice_data = ChatCompletionResponseStreamChoice(
-            index=0, delta=ChatCompletionMessage(), finish_reason=Finish.STOP
-        )
-        chunk = ChatCompletionStreamResponse(model=request.model, choices=[choice_data])
-        yield jsonify(chunk)
-        yield "[DONE]"
-
-    @app.post("/v1/score/evaluation", response_model=ScoreEvaluationResponse, status_code=status.HTTP_200_OK)
     async def create_score_evaluation(request: ScoreEvaluationRequest):
         if chat_model.engine.can_generate:
             raise HTTPException(status_code=status.HTTP_405_METHOD_NOT_ALLOWED, detail="Not allowed")
 
-        if len(request.messages) == 0:
-            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid request")
-
-        scores = await chat_model.aget_scores(request.messages, max_length=request.max_length)
-        return ScoreEvaluationResponse(model=request.model, scores=scores)
+        return await create_score_evaluation_response(request, chat_model)
 
     return app
 
 
-if __name__ == "__main__":
+def run_api() -> None:
     chat_model = ChatModel()
     app = create_app(chat_model)
-    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("API_PORT", 8000)), workers=1)
+    api_host = os.environ.get("API_HOST", "0.0.0.0")
+    api_port = int(os.environ.get("API_PORT", "8000"))
+    print("Visit http://localhost:{}/docs for API document.".format(api_port))
+    uvicorn.run(app, host=api_host, port=api_port)

src/llmtuner/api/chat.py

@@ -0,0 +1,186 @@
+import json
+import uuid
+from typing import TYPE_CHECKING, AsyncGenerator, Dict, List, Optional, Tuple
+
+from ..data import Role as DataRole
+from ..extras.logging import get_logger
+from ..extras.packages import is_fastapi_available
+from .common import dictify, jsonify
+from .protocol import (
+    ChatCompletionMessage,
+    ChatCompletionResponse,
+    ChatCompletionResponseChoice,
+    ChatCompletionResponseUsage,
+    ChatCompletionStreamResponse,
+    ChatCompletionStreamResponseChoice,
+    Finish,
+    Function,
+    FunctionCall,
+    Role,
+    ScoreEvaluationResponse,
+)
+
+
+if is_fastapi_available():
+    from fastapi import HTTPException, status
+
+
+if TYPE_CHECKING:
+    from ..chat import ChatModel
+    from .protocol import ChatCompletionRequest, ScoreEvaluationRequest
+
+
+logger = get_logger(__name__)
+ROLE_MAPPING = {
+    Role.USER: DataRole.USER.value,
+    Role.ASSISTANT: DataRole.ASSISTANT.value,
+    Role.SYSTEM: DataRole.SYSTEM.value,
+    Role.FUNCTION: DataRole.FUNCTION.value,
+    Role.TOOL: DataRole.OBSERVATION.value,
+}
+
+
+def _process_request(request: "ChatCompletionRequest") -> Tuple[List[Dict[str, str]], str, str]:
+    logger.info("==== request ====\n{}".format(json.dumps(dictify(request), indent=2, ensure_ascii=False)))
+
+    if len(request.messages) == 0:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length")
+
+    if request.messages[0].role == Role.SYSTEM:
+        system = request.messages.pop(0).content
+    else:
+        system = ""
+
+    if len(request.messages) % 2 == 0:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Only supports u/a/u/a/u...")
+
+    input_messages = []
+    for i, message in enumerate(request.messages):
+        if i % 2 == 0 and message.role not in [Role.USER, Role.TOOL]:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
+        elif i % 2 == 1 and message.role not in [Role.ASSISTANT, Role.FUNCTION]:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid role")
+
+        if message.role == Role.ASSISTANT and isinstance(message.tool_calls, list) and len(message.tool_calls):
+            name = message.tool_calls[0].function.name
+            arguments = message.tool_calls[0].function.arguments
+            content = json.dumps({"name": name, "argument": arguments}, ensure_ascii=False)
+            input_messages.append({"role": ROLE_MAPPING[Role.FUNCTION], "content": content})
+        else:
+            input_messages.append({"role": ROLE_MAPPING[message.role], "content": message.content})
+
+    tool_list = request.tools
+    if isinstance(tool_list, list) and len(tool_list):
+        try:
+            tools = json.dumps([dictify(tool.function) for tool in tool_list], ensure_ascii=False)
+        except Exception:
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid tools")
+    else:
+        tools = ""
+
+    return input_messages, system, tools
+
+
+def _create_stream_chat_completion_chunk(
+    completion_id: str,
+    model: str,
+    delta: "ChatCompletionMessage",
+    index: Optional[int] = 0,
+    finish_reason: Optional["Finish"] = None,
+) -> str:
+    choice_data = ChatCompletionStreamResponseChoice(index=index, delta=delta, finish_reason=finish_reason)
+    chunk = ChatCompletionStreamResponse(id=completion_id, model=model, choices=[choice_data])
+    return jsonify(chunk)
+
+
+async def create_chat_completion_response(
+    request: "ChatCompletionRequest", chat_model: "ChatModel"
+) -> "ChatCompletionResponse":
+    completion_id = "chatcmpl-{}".format(uuid.uuid4().hex)
+    input_messages, system, tools = _process_request(request)
+    responses = await chat_model.achat(
+        input_messages,
+        system,
+        tools,
+        do_sample=request.do_sample,
+        temperature=request.temperature,
+        top_p=request.top_p,
+        max_new_tokens=request.max_tokens,
+        num_return_sequences=request.n,
+        stop=request.stop,
+    )
+
+    prompt_length, response_length = 0, 0
+    choices = []
+    for i, response in enumerate(responses):
+        if tools:
+            result = chat_model.engine.template.format_tools.extract(response.response_text)
+        else:
+            result = response.response_text
+
+        if isinstance(result, tuple):
+            name, arguments = result
+            function = Function(name=name, arguments=arguments)
+            tool_call = FunctionCall(id="call_{}".format(uuid.uuid4().hex), function=function)
+            response_message = ChatCompletionMessage(role=Role.ASSISTANT, tool_calls=[tool_call])
+            finish_reason = Finish.TOOL
+        else:
+            response_message = ChatCompletionMessage(role=Role.ASSISTANT, content=result)
+            finish_reason = Finish.STOP if response.finish_reason == "stop" else Finish.LENGTH
+
+        choices.append(ChatCompletionResponseChoice(index=i, message=response_message, finish_reason=finish_reason))
+        prompt_length = response.prompt_length
+        response_length += response.response_length
+
+    usage = ChatCompletionResponseUsage(
+        prompt_tokens=prompt_length,
+        completion_tokens=response_length,
+        total_tokens=prompt_length + response_length,
+    )
+
+    return ChatCompletionResponse(id=completion_id, model=request.model, choices=choices, usage=usage)
+
+
+async def create_stream_chat_completion_response(
+    request: "ChatCompletionRequest", chat_model: "ChatModel"
+) -> AsyncGenerator[str, None]:
+    completion_id = "chatcmpl-{}".format(uuid.uuid4().hex)
+    input_messages, system, tools = _process_request(request)
+    if tools:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Cannot stream function calls.")
+
+    if request.n > 1:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Cannot stream multiple responses.")
+
+    yield _create_stream_chat_completion_chunk(
+        completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(role=Role.ASSISTANT, content="")
+    )
+    async for new_token in chat_model.astream_chat(
+        input_messages,
+        system,
+        tools,
+        do_sample=request.do_sample,
+        temperature=request.temperature,
+        top_p=request.top_p,
+        max_new_tokens=request.max_tokens,
+        stop=request.stop,
+    ):
+        if len(new_token) != 0:
+            yield _create_stream_chat_completion_chunk(
+                completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(content=new_token)
+            )
+
+    yield _create_stream_chat_completion_chunk(
+        completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(), finish_reason=Finish.STOP
+    )
+    yield "[DONE]"
+
+
+async def create_score_evaluation_response(
+    request: "ScoreEvaluationRequest", chat_model: "ChatModel"
+) -> "ScoreEvaluationResponse":
+    if len(request.messages) == 0:
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid request")
+
+    scores = await chat_model.aget_scores(request.messages, max_length=request.max_length)
+    return ScoreEvaluationResponse(model=request.model, scores=scores)

src/llmtuner/api/common.py

@@ -0,0 +1,20 @@
+import json
+from typing import TYPE_CHECKING, Any, Dict
+
+
+if TYPE_CHECKING:
+    from pydantic import BaseModel
+
+
+def dictify(data: "BaseModel") -> Dict[str, Any]:
+    try:  # pydantic v2
+        return data.model_dump(exclude_unset=True)
+    except AttributeError:  # pydantic v1
+        return data.dict(exclude_unset=True)
+
+
+def jsonify(data: "BaseModel") -> str:
+    try:  # pydantic v2
+        return json.dumps(data.model_dump(exclude_unset=True), ensure_ascii=False)
+    except AttributeError:  # pydantic v1
+        return data.json(exclude_unset=True, ensure_ascii=False)

src/llmtuner/api/protocol.py

@@ -1,6 +1,6 @@
 import time
 from enum import Enum, unique
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Union
 
 from pydantic import BaseModel, Field
 from typing_extensions import Literal
@@ -51,7 +51,7 @@ class FunctionAvailable(BaseModel):
 
 
 class FunctionCall(BaseModel):
-    id: Literal["call_default"] = "call_default"
+    id: str
     type: Literal["function"] = "function"
     function: Function
 
@@ -77,6 +77,7 @@ class ChatCompletionRequest(BaseModel):
     top_p: Optional[float] = None
     n: int = 1
     max_tokens: Optional[int] = None
+    stop: Optional[Union[str, List[str]]] = None
     stream: bool = False
 
 
@@ -86,7 +87,7 @@ class ChatCompletionResponseChoice(BaseModel):
     finish_reason: Finish
 
 
-class ChatCompletionResponseStreamChoice(BaseModel):
+class ChatCompletionStreamResponseChoice(BaseModel):
     index: int
     delta: ChatCompletionMessage
     finish_reason: Optional[Finish] = None
@@ -99,7 +100,7 @@ class ChatCompletionResponseUsage(BaseModel):
 
 
 class ChatCompletionResponse(BaseModel):
-    id: Literal["chatcmpl-default"] = "chatcmpl-default"
+    id: str
     object: Literal["chat.completion"] = "chat.completion"
     created: int = Field(default_factory=lambda: int(time.time()))
     model: str
@@ -108,11 +109,11 @@ class ChatCompletionResponse(BaseModel):
 
 
 class ChatCompletionStreamResponse(BaseModel):
-    id: Literal["chatcmpl-default"] = "chatcmpl-default"
+    id: str
     object: Literal["chat.completion.chunk"] = "chat.completion.chunk"
     created: int = Field(default_factory=lambda: int(time.time()))
     model: str
-    choices: List[ChatCompletionResponseStreamChoice]
+    choices: List[ChatCompletionStreamResponseChoice]
 
 
 class ScoreEvaluationRequest(BaseModel):
@@ -122,7 +123,7 @@ class ScoreEvaluationRequest(BaseModel):
 
 
 class ScoreEvaluationResponse(BaseModel):
-    id: Literal["scoreeval-default"] = "scoreeval-default"
+    id: str
     object: Literal["score.evaluation"] = "score.evaluation"
     model: str
     scores: List[float]

src/llmtuner/chat/base_engine.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, List, Literal, Opti
 
 
 if TYPE_CHECKING:
+    from numpy.typing import NDArray
     from transformers import PreTrainedModel, PreTrainedTokenizer
     from vllm import AsyncLLMEngine
 
@@ -46,6 +47,7 @@ class BaseEngine(ABC):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> List["Response"]: ...
 
@@ -55,6 +57,7 @@ class BaseEngine(ABC):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> AsyncGenerator[str, None]: ...
 

src/llmtuner/chat/chat_model.py

@@ -2,12 +2,15 @@ import asyncio
 from threading import Thread
 from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, Generator, List, Optional, Sequence
 
+from ..extras.misc import torch_gc
 from ..hparams import get_infer_args
 from .hf_engine import HuggingfaceEngine
 from .vllm_engine import VllmEngine
 
 
 if TYPE_CHECKING:
+    from numpy.typing import NDArray
+
     from .base_engine import BaseEngine, Response
 
 
@@ -36,9 +39,10 @@ class ChatModel:
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> List["Response"]:
-        task = asyncio.run_coroutine_threadsafe(self.achat(messages, system, tools, **input_kwargs), self._loop)
+        task = asyncio.run_coroutine_threadsafe(self.achat(messages, system, tools, image, **input_kwargs), self._loop)
         return task.result()
 
     async def achat(
@@ -46,18 +50,20 @@ class ChatModel:
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> List["Response"]:
-        return await self.engine.chat(messages, system, tools, **input_kwargs)
+        return await self.engine.chat(messages, system, tools, image, **input_kwargs)
 
     def stream_chat(
         self,
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> Generator[str, None, None]:
-        generator = self.astream_chat(messages, system, tools, **input_kwargs)
+        generator = self.astream_chat(messages, system, tools, image, **input_kwargs)
         while True:
             try:
                 task = asyncio.run_coroutine_threadsafe(generator.__anext__(), self._loop)
@@ -70,9 +76,10 @@ class ChatModel:
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> AsyncGenerator[str, None]:
-        async for new_token in self.engine.stream_chat(messages, system, tools, **input_kwargs):
+        async for new_token in self.engine.stream_chat(messages, system, tools, image, **input_kwargs):
             yield new_token
 
     def get_scores(
@@ -89,3 +96,45 @@ class ChatModel:
         **input_kwargs,
     ) -> List[float]:
         return await self.engine.get_scores(batch_input, **input_kwargs)
+
+
+def run_chat() -> None:
+    try:
+        import platform
+
+        if platform.system() != "Windows":
+            import readline  # noqa: F401
+    except ImportError:
+        print("Install `readline` for a better experience.")
+
+    chat_model = ChatModel()
+    messages = []
+    print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.")
+
+    while True:
+        try:
+            query = input("\nUser: ")
+        except UnicodeDecodeError:
+            print("Detected decoding error at the inputs, please set the terminal encoding to utf-8.")
+            continue
+        except Exception:
+            raise
+
+        if query.strip() == "exit":
+            break
+
+        if query.strip() == "clear":
+            messages = []
+            torch_gc()
+            print("History has been removed.")
+            continue
+
+        messages.append({"role": "user", "content": query})
+        print("Assistant: ", end="", flush=True)
+
+        response = ""
+        for new_text in chat_model.stream_chat(messages):
+            print(new_text, end="", flush=True)
+            response += new_text
+        print()
+        messages.append({"role": "assistant", "content": response})

src/llmtuner/chat/hf_engine.py

@@ -14,7 +14,9 @@ from .base_engine import BaseEngine, Response
 
 
 if TYPE_CHECKING:
-    from transformers import PreTrainedModel, PreTrainedTokenizer
+    from numpy.typing import NDArray
+    from transformers import PreTrainedModel, PreTrainedTokenizer, ProcessorMixin
+    from transformers.image_processing_utils import BaseImageProcessor
     from trl import PreTrainedModelWrapper
 
     from ..data import Template
@@ -30,7 +32,9 @@ class HuggingfaceEngine(BaseEngine):
         generating_args: "GeneratingArguments",
     ) -> None:
         self.can_generate = finetuning_args.stage == "sft"
-        self.tokenizer = load_tokenizer(model_args)
+        tokenizer_module = load_tokenizer(model_args)
+        self.tokenizer = tokenizer_module["tokenizer"]
+        self.processor = tokenizer_module["processor"]
         self.tokenizer.padding_side = "left" if self.can_generate else "right"
         self.template = get_template_and_fix_tokenizer(self.tokenizer, data_args.template)
         self.model = load_model(
@@ -42,13 +46,18 @@ class HuggingfaceEngine(BaseEngine):
     def _process_args(
         model: "PreTrainedModel",
         tokenizer: "PreTrainedTokenizer",
+        processor: Optional["ProcessorMixin"],
         template: "Template",
         generating_args: Dict[str, Any],
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         input_kwargs: Optional[Dict[str, Any]] = {},
     ) -> Tuple[Dict[str, Any], int]:
+        if processor is not None and image is not None and "<image>" not in messages[0]["content"]:
+            messages[0]["content"] = "<image>" + messages[0]["content"]
+
         paired_messages = messages + [{"role": "assistant", "content": ""}]
         prompt_ids, _ = template.encode_oneturn(
             tokenizer=tokenizer, messages=paired_messages, system=system, tools=tools
@@ -56,23 +65,30 @@ class HuggingfaceEngine(BaseEngine):
         prompt_length = len(prompt_ids)
         inputs = torch.tensor([prompt_ids], device=model.device)
 
-        do_sample = input_kwargs.pop("do_sample", None)
-        temperature = input_kwargs.pop("temperature", None)
-        top_p = input_kwargs.pop("top_p", None)
-        top_k = input_kwargs.pop("top_k", None)
-        num_return_sequences = input_kwargs.pop("num_return_sequences", None)
-        repetition_penalty = input_kwargs.pop("repetition_penalty", None)
+        do_sample = input_kwargs.pop("do_sample", generating_args["do_sample"])
+        temperature = input_kwargs.pop("temperature", generating_args["temperature"])
+        top_p = input_kwargs.pop("top_p", generating_args["top_p"])
+        top_k = input_kwargs.pop("top_k", generating_args["top_k"])
+        num_return_sequences = input_kwargs.pop("num_return_sequences", 1)
+        repetition_penalty = input_kwargs.pop("repetition_penalty", generating_args["repetition_penalty"])
+        length_penalty = input_kwargs.pop("length_penalty", generating_args["length_penalty"])
         max_length = input_kwargs.pop("max_length", None)
         max_new_tokens = input_kwargs.pop("max_new_tokens", None)
+        stop = input_kwargs.pop("stop", None)
 
+        if stop is not None:
+            raise ValueError("Stop parameter is not supported in Huggingface engine yet.")
+
+        generating_args = generating_args.copy()
         generating_args.update(
             dict(
-                do_sample=do_sample if do_sample is not None else generating_args["do_sample"],
-                temperature=temperature or generating_args["temperature"],
-                top_p=top_p or generating_args["top_p"],
-                top_k=top_k or generating_args["top_k"],
-                num_return_sequences=num_return_sequences or 1,
-                repetition_penalty=repetition_penalty or generating_args["repetition_penalty"],
+                do_sample=do_sample,
+                temperature=temperature,
+                top_p=top_p,
+                top_k=top_k,
+                num_return_sequences=num_return_sequences,
+                repetition_penalty=repetition_penalty,
+                length_penalty=length_penalty,
                 eos_token_id=[tokenizer.eos_token_id] + tokenizer.additional_special_tokens_ids,
                 pad_token_id=tokenizer.pad_token_id,
             )
@@ -81,6 +97,10 @@ class HuggingfaceEngine(BaseEngine):
         if isinstance(num_return_sequences, int) and num_return_sequences > 1:
             generating_args["do_sample"] = True
 
+        if not generating_args["do_sample"]:
+            generating_args.pop("temperature", None)
+            generating_args.pop("top_p", None)
+
         if max_length:
             generating_args.pop("max_new_tokens", None)
             generating_args["max_length"] = max_length
@@ -95,6 +115,11 @@ class HuggingfaceEngine(BaseEngine):
             logits_processor=get_logits_processor(),
         )
 
+        if processor is not None and image is not None:
+            image_processor: "BaseImageProcessor" = getattr(processor, "image_processor")
+            pixel_values: "torch.Tensor" = image_processor(image, return_tensors="pt")["pixel_values"]
+            gen_kwargs["pixel_values"] = pixel_values.to(model.device)
+
         return gen_kwargs, prompt_length
 
     @staticmethod
@@ -102,15 +127,17 @@ class HuggingfaceEngine(BaseEngine):
     def _chat(
         model: "PreTrainedModel",
         tokenizer: "PreTrainedTokenizer",
+        processor: Optional["ProcessorMixin"],
         template: "Template",
         generating_args: Dict[str, Any],
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         input_kwargs: Optional[Dict[str, Any]] = {},
     ) -> List["Response"]:
         gen_kwargs, prompt_length = HuggingfaceEngine._process_args(
-            model, tokenizer, template, generating_args, messages, system, tools, input_kwargs
+            model, tokenizer, processor, template, generating_args, messages, system, tools, image, input_kwargs
         )
         generate_output = model.generate(**gen_kwargs)
         response_ids = generate_output[:, prompt_length:]
@@ -135,15 +162,17 @@ class HuggingfaceEngine(BaseEngine):
     def _stream_chat(
         model: "PreTrainedModel",
         tokenizer: "PreTrainedTokenizer",
+        processor: Optional["ProcessorMixin"],
         template: "Template",
         generating_args: Dict[str, Any],
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         input_kwargs: Optional[Dict[str, Any]] = {},
     ) -> Callable[[], str]:
         gen_kwargs, _ = HuggingfaceEngine._process_args(
-            model, tokenizer, template, generating_args, messages, system, tools, input_kwargs
+            model, tokenizer, processor, template, generating_args, messages, system, tools, image, input_kwargs
         )
         streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
         gen_kwargs["streamer"] = streamer
@@ -199,6 +228,7 @@ class HuggingfaceEngine(BaseEngine):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> List["Response"]:
         if not self.can_generate:
@@ -208,11 +238,13 @@ class HuggingfaceEngine(BaseEngine):
         input_args = (
             self.model,
             self.tokenizer,
+            self.processor,
             self.template,
             self.generating_args,
             messages,
             system,
             tools,
+            image,
             input_kwargs,
         )
         async with self._semaphore:
@@ -224,6 +256,7 @@ class HuggingfaceEngine(BaseEngine):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> AsyncGenerator[str, None]:
         if not self.can_generate:
@@ -233,11 +266,13 @@ class HuggingfaceEngine(BaseEngine):
         input_args = (
             self.model,
             self.tokenizer,
+            self.processor,
             self.template,
             self.generating_args,
             messages,
             system,
             tools,
+            image,
             input_kwargs,
         )
         async with self._semaphore:

src/llmtuner/chat/vllm_engine.py

@@ -2,19 +2,31 @@ import uuid
 from typing import TYPE_CHECKING, AsyncGenerator, AsyncIterator, Dict, List, Optional, Sequence
 
 from ..data import get_template_and_fix_tokenizer
-from ..extras.misc import get_device_count
+from ..extras.logging import get_logger
+from ..extras.misc import get_device_count, infer_optim_dtype
 from ..extras.packages import is_vllm_available
-from ..model import load_tokenizer
+from ..model import load_config, load_tokenizer
+from ..model.utils.visual import LlavaMultiModalProjectorForYiVLForVLLM
 from .base_engine import BaseEngine, Response
 
 
 if is_vllm_available():
     from vllm import AsyncEngineArgs, AsyncLLMEngine, RequestOutput, SamplingParams
+    from vllm.lora.request import LoRARequest
+    from vllm.sequence import MultiModalData
+
 
 if TYPE_CHECKING:
+    import torch
+    from numpy.typing import NDArray
+    from transformers.image_processing_utils import BaseImageProcessor
+
     from ..hparams import DataArguments, FinetuningArguments, GeneratingArguments, ModelArguments
 
 
+logger = get_logger(__name__)
+
+
 class VllmEngine(BaseEngine):
     def __init__(
         self,
@@ -23,76 +35,117 @@ class VllmEngine(BaseEngine):
         finetuning_args: "FinetuningArguments",
         generating_args: "GeneratingArguments",
     ) -> None:
+        config = load_config(model_args)  # may download model from ms hub
+        infer_dtype = infer_optim_dtype(model_dtype=getattr(config, "torch_dtype", None))
+        infer_dtype = str(infer_dtype).split(".")[-1]
+
         self.can_generate = finetuning_args.stage == "sft"
-        engine_args = AsyncEngineArgs(
-            model=model_args.model_name_or_path,
-            trust_remote_code=True,
-            max_model_len=model_args.vllm_maxlen,
-            tensor_parallel_size=get_device_count() or 1,
-            gpu_memory_utilization=model_args.vllm_gpu_util,
-            disable_log_stats=True,
-            disable_log_requests=True,
-            enforce_eager=model_args.vllm_enforce_eager,
-        )
-        self.model = AsyncLLMEngine.from_engine_args(engine_args)
-        self.tokenizer = load_tokenizer(model_args)
+        tokenizer_module = load_tokenizer(model_args)
+        self.tokenizer = tokenizer_module["tokenizer"]
+        self.processor = tokenizer_module["processor"]
         self.tokenizer.padding_side = "left"
         self.template = get_template_and_fix_tokenizer(self.tokenizer, data_args.template)
         self.generating_args = generating_args.to_dict()
 
+        engine_args = {
+            "model": model_args.model_name_or_path,
+            "trust_remote_code": True,
+            "download_dir": model_args.cache_dir,
+            "dtype": infer_dtype,
+            "max_model_len": model_args.vllm_maxlen,
+            "tensor_parallel_size": get_device_count() or 1,
+            "gpu_memory_utilization": model_args.vllm_gpu_util,
+            "disable_log_stats": True,
+            "disable_log_requests": True,
+            "enforce_eager": model_args.vllm_enforce_eager,
+            "enable_lora": model_args.adapter_name_or_path is not None,
+        }
+
+        if model_args.visual_inputs:
+            image_size = config.vision_config.image_size
+            patch_size = config.vision_config.patch_size
+            self.image_feature_size = (image_size // patch_size) ** 2
+            engine_args["image_input_type"] = "pixel_values"
+            engine_args["image_token_id"] = self.tokenizer.convert_tokens_to_ids("<image>")
+            engine_args["image_input_shape"] = "1,3,{},{}".format(image_size, image_size)
+            engine_args["image_feature_size"] = self.image_feature_size
+            if getattr(config, "is_yi_vl_derived_model", None):
+                # bug in vllm 0.4.2, see: https://github.com/vllm-project/vllm/pull/4828
+                import vllm.model_executor.models.llava
+
+                logger.info("Detected Yi-VL model, applying projector patch.")
+                vllm.model_executor.models.llava.LlavaMultiModalProjector = LlavaMultiModalProjectorForYiVLForVLLM
+
+        self.model = AsyncLLMEngine.from_engine_args(AsyncEngineArgs(**engine_args))
+        if model_args.adapter_name_or_path is not None:
+            self.lora_request = LoRARequest("default", 1, model_args.adapter_name_or_path[0])
+        else:
+            self.lora_request = None
+
     async def _generate(
         self,
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> AsyncIterator["RequestOutput"]:
         request_id = "chatcmpl-{}".format(uuid.uuid4().hex)
+        if self.processor is not None and image is not None and "<image>" not in messages[0]["content"]:
+            messages[0]["content"] = "<image>" * self.image_feature_size + messages[0]["content"]
+
         paired_messages = messages + [{"role": "assistant", "content": ""}]
         prompt_ids, _ = self.template.encode_oneturn(
             tokenizer=self.tokenizer, messages=paired_messages, system=system, tools=tools
         )
         prompt_length = len(prompt_ids)
 
-        temperature = input_kwargs.pop("temperature", None)
-        top_p = input_kwargs.pop("top_p", None)
-        top_k = input_kwargs.pop("top_k", None)
-        num_return_sequences = input_kwargs.pop("num_return_sequences", None)
-        repetition_penalty = input_kwargs.pop("repetition_penalty", None)
+        use_beam_search = self.generating_args["num_beams"] > 1
+        temperature = input_kwargs.pop("temperature", self.generating_args["temperature"])
+        top_p = input_kwargs.pop("top_p", self.generating_args["top_p"])
+        top_k = input_kwargs.pop("top_k", self.generating_args["top_k"])
+        num_return_sequences = input_kwargs.pop("num_return_sequences", 1)
+        repetition_penalty = input_kwargs.pop("repetition_penalty", self.generating_args["repetition_penalty"])
+        length_penalty = input_kwargs.pop("length_penalty", self.generating_args["length_penalty"])
         max_length = input_kwargs.pop("max_length", None)
         max_new_tokens = input_kwargs.pop("max_new_tokens", None)
+        stop = input_kwargs.pop("stop", None)
 
-        generating_args = self.generating_args.copy()
-        generating_args.update(
-            dict(
-                temperature=temperature or generating_args["temperature"],
-                top_p=top_p or generating_args["top_p"],
-                top_k=top_k or generating_args["top_k"],
-                num_return_sequences=num_return_sequences or 1,
-                repetition_penalty=repetition_penalty or generating_args["repetition_penalty"],
-            )
-        )
-
+        max_tokens = self.generating_args["max_new_tokens"] or self.generating_args["max_length"]
         if max_length:
-            generating_args["max_new_tokens"] = max_length - prompt_length
+            max_tokens = max_length - prompt_length if max_length > prompt_length else 1
 
         if max_new_tokens:
-            generating_args["max_new_tokens"] = max_new_tokens
+            max_tokens = max_new_tokens
 
         sampling_params = SamplingParams(
-            n=generating_args["num_return_sequences"],
-            repetition_penalty=generating_args["repetition_penalty"],
-            temperature=generating_args["temperature"],
-            top_p=generating_args["top_p"],
-            top_k=generating_args["top_k"],
-            use_beam_search=generating_args["num_beams"] > 1,
-            length_penalty=generating_args["length_penalty"],
+            n=num_return_sequences,
+            repetition_penalty=repetition_penalty,
+            temperature=temperature,
+            top_p=top_p,
+            top_k=top_k,
+            use_beam_search=use_beam_search,
+            length_penalty=length_penalty,
+            stop=stop,
             stop_token_ids=[self.tokenizer.eos_token_id] + self.tokenizer.additional_special_tokens_ids,
-            max_tokens=generating_args["max_new_tokens"],
+            max_tokens=max_tokens,
             skip_special_tokens=True,
         )
+
+        if self.processor is not None and image is not None:
+            image_processor: "BaseImageProcessor" = getattr(self.processor, "image_processor")
+            pixel_values: "torch.Tensor" = image_processor(image, return_tensors="pt")["pixel_values"]
+            multi_modal_data = MultiModalData(type=MultiModalData.Type.IMAGE, data=pixel_values)
+        else:
+            multi_modal_data = None
+
         result_generator = self.model.generate(
-            prompt=None, sampling_params=sampling_params, request_id=request_id, prompt_token_ids=prompt_ids
+            prompt=None,
+            sampling_params=sampling_params,
+            request_id=request_id,
+            prompt_token_ids=prompt_ids,
+            lora_request=self.lora_request,
+            multi_modal_data=multi_modal_data,
         )
         return result_generator
 
@@ -104,10 +157,11 @@ class VllmEngine(BaseEngine):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> List["Response"]:
         final_output = None
-        generator = await self._generate(messages, system, tools, **input_kwargs)
+        generator = await self._generate(messages, system, tools, image, **input_kwargs)
         async for request_output in generator:
             final_output = request_output
 
@@ -129,10 +183,11 @@ class VllmEngine(BaseEngine):
         messages: Sequence[Dict[str, str]],
         system: Optional[str] = None,
         tools: Optional[str] = None,
+        image: Optional["NDArray"] = None,
         **input_kwargs,
     ) -> AsyncGenerator[str, None]:
         generated_text = ""
-        generator = await self._generate(messages, system, tools, **input_kwargs)
+        generator = await self._generate(messages, system, tools, image, **input_kwargs)
         async for result in generator:
             delta_text = result.outputs[0].text[len(generated_text) :]
             generated_text = result.outputs[0].text

src/llmtuner/cli.py

@@ -0,0 +1,75 @@
+import sys
+from enum import Enum, unique
+
+from .api.app import run_api
+from .chat.chat_model import run_chat
+from .eval.evaluator import run_eval
+from .train.tuner import export_model, run_exp
+from .webui.interface import run_web_demo, run_web_ui
+
+
+USAGE = (
+    "-" * 70
+    + "\n"
+    + "| Usage:                                                             |\n"
+    + "|   llamafactory-cli api -h: launch an OpenAI-style API server       |\n"
+    + "|   llamafactory-cli chat -h: launch a chat interface in CLI         |\n"
+    + "|   llamafactory-cli eval -h: evaluate models                        |\n"
+    + "|   llamafactory-cli export -h: merge LoRA adapters and export model |\n"
+    + "|   llamafactory-cli train -h: train models                          |\n"
+    + "|   llamafactory-cli webchat -h: launch a chat interface in Web UI   |\n"
+    + "|   llamafactory-cli webui: launch LlamaBoard                        |\n"
+    + "|   llamafactory-cli version: show version info                      |\n"
+    + "-" * 70
+)
+
+VERSION = "0.7.1"
+
+WELCOME = (
+    "-" * 58
+    + "\n"
+    + "| Welcome to LLaMA Factory, version {}".format(VERSION)
+    + " " * (21 - len(VERSION))
+    + "|\n|"
+    + " " * 56
+    + "|\n"
+    + "| Project page: https://github.com/hiyouga/LLaMA-Factory |\n"
+    + "-" * 58
+)
+
+
+@unique
+class Command(str, Enum):
+    API = "api"
+    CHAT = "chat"
+    EVAL = "eval"
+    EXPORT = "export"
+    TRAIN = "train"
+    WEBDEMO = "webchat"
+    WEBUI = "webui"
+    VER = "version"
+    HELP = "help"
+
+
+def main():
+    command = sys.argv.pop(1)
+    if command == Command.API:
+        run_api()
+    elif command == Command.CHAT:
+        run_chat()
+    elif command == Command.EVAL:
+        run_eval()
+    elif command == Command.EXPORT:
+        export_model()
+    elif command == Command.TRAIN:
+        run_exp()
+    elif command == Command.WEBDEMO:
+        run_web_demo()
+    elif command == Command.WEBUI:
+        run_web_ui()
+    elif command == Command.VER:
+        print(WELCOME)
+    elif command == Command.HELP:
+        print(USAGE)
+    else:
+        raise NotImplementedError("Unknown command: {}".format(command))