From 949e5fe63811afb05cc687a2117295d494979b69 Mon Sep 17 00:00:00 2001 From: hiyouga Date: Tue, 2 Apr 2024 20:22:11 +0800 Subject: [PATCH] update readme --- README.md | 27 +++++++++++++++------------ README_zh.md | 27 +++++++++++++++------------ 2 files changed, 30 insertions(+), 24 deletions(-) diff --git a/README.md b/README.md index 6450e61e..99278fbc 100644 --- a/README.md +++ b/README.md @@ -307,8 +307,7 @@ cd LLaMA-Factory pip install -e .[metrics] ``` -> [!TIP] -> Extra dependencies available: deepspeed, metrics, unsloth, vllm, bitsandbytes, gptq, awq, aqlm, qwen, quality +Extra dependencies available: deepspeed, metrics, unsloth, vllm, bitsandbytes, gptq, awq, aqlm, qwen, quality
For Windows users @@ -324,6 +323,9 @@ To enable FlashAttention-2 on the Windows platform, you need to install the prec ### LLaMA Board GUI +> [!IMPORTANT] +> LLaMA Board GUI only supports training on a single GPU, please use [CLI](#command-line-interface) for distributed training. + #### Use local environment ```bash @@ -335,7 +337,6 @@ CUDA_VISIBLE_DEVICES=0 python src/train_web.py ```bash docker build -f ./Dockerfile -t llama-factory:latest . - docker run --gpus=all \ -v ./hf_cache:/root/.cache/huggingface/ \ -v ./data:/app/data \ @@ -353,14 +354,13 @@ docker run --gpus=all \ docker compose -f ./docker-compose.yml up -d ``` -> [!TIP] -> Details about volume: -> * hf_cache: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory. -> * data: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI. -> * output: Set export dir to this location so that the merged result can be accessed directly on the host machine. +
Details about volume -> [!WARNING] -> LLaMA Board GUI does not yet support multi-GPUs training. +- hf_cache: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory. +- data: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI. +- output: Set export dir to this location so that the merged result can be accessed directly on the host machine. + +
### Command Line Interface @@ -377,11 +377,12 @@ 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 ``` -> [!TIP] -> 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., `modelscope/Llama-2-7b-ms`. ## Projects using LLaMA Factory +
Click to show + 1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223) 1. Yu et al. Open, Closed, or Small Language Models for Text Classification? 2023. [[arxiv]](https://arxiv.org/abs/2308.10092) 1. Wang et al. UbiPhysio: Support Daily Functioning, Fitness, and Rehabilitation with Action Understanding and Feedback in Natural Language. 2023. [[arxiv]](https://arxiv.org/abs/2308.10526) @@ -411,6 +412,8 @@ export USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows 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. +
+ > [!TIP] > If you have a project that should be incorporated, please contact via email or create a pull request. diff --git a/README_zh.md b/README_zh.md index 8b19f17f..d6dea04d 100644 --- a/README_zh.md +++ b/README_zh.md @@ -307,8 +307,7 @@ cd LLaMA-Factory pip install -e .[metrics] ``` -> [!TIP] -> 可选的额外依赖项：deepspeed、metrics、unsloth、vllm、bitsandbytes、gptq、awq、aqlm、qwen、quality +可选的额外依赖项：deepspeed、metrics、unsloth、vllm、bitsandbytes、gptq、awq、aqlm、qwen、quality
Windows 用户指南 @@ -324,6 +323,9 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl ### LLaMA Board 可视化界面 +> [!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。 + #### 使用本地环境 ```bash @@ -331,7 +333,6 @@ CUDA_VISIBLE_DEVICES=0 python src/train_web.py # 或 CUDA_VISIBLE_DEVICES=0 python -m llmtuner.webui.interface ``` - #### 使用 Docker ```bash @@ -354,14 +355,13 @@ docker run --gpus=all \ docker compose -f ./docker-compose.yml up -d ``` -> [!TIP] -> 数据卷详情： -> * hf_cache：使用宿主机的 Hugging Face 缓存文件夹，允许更改为新的目录。 -> * data：宿主机中存放数据集的文件夹路径。 -> * output：将导出目录设置为该路径后，即可在宿主机中访问导出后的模型。 +
数据卷详情 -> [!WARNING] -> LLaMA Board 可视化界面尚不支持多 GPU 训练。 +- hf_cache：使用宿主机的 Hugging Face 缓存文件夹，允许更改为新的目录。 +- data：宿主机中存放数据集的文件夹路径。 +- output：将导出目录设置为该路径后，即可在宿主机中访问导出后的模型。 + +
### 命令行接口 @@ -378,11 +378,12 @@ docker compose -f ./docker-compose.yml up -d export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1` ``` -> [!TIP] -> 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 `modelscope/Llama-2-7b-ms`。 ## 使用了 LLaMA Factory 的项目 +
点击显示 + 1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223) 1. Yu et al. Open, Closed, or Small Language Models for Text Classification? 2023. [[arxiv]](https://arxiv.org/abs/2308.10092) 1. Wang et al. UbiPhysio: Support Daily Functioning, Fitness, and Rehabilitation with Action Understanding and Feedback in Natural Language. 2023. [[arxiv]](https://arxiv.org/abs/2308.10526) @@ -412,6 +413,8 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1` 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。 +
+ > [!TIP] > 如果您有项目希望添加至上述列表，请通过邮件联系或者创建一个 PR。