From 0a0dcb5c3f10bca7d1c6a23e39e88111d0d63965 Mon Sep 17 00:00:00 2001 From: HIT-cwh <2892770585@qq.com> Date: Wed, 30 Aug 2023 15:28:58 +0800 Subject: [PATCH] update readme --- README.md | 13 +++++++------ README_zh-CN.md | 13 +++++++------ 2 files changed, 14 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index aad0aa251..f364c4206 100644 --- a/README.md +++ b/README.md @@ -14,14 +14,14 @@ English | [简体中文](README_zh-CN.md) ## 🎉 News -- **\[2023.08.xx\]** XTuner is released, with multiple fine-tuned adapters on [HuggingFace](https://huggingface.co/xtuner). +- **\[2023.08.30\]** XTuner is released, with multiple fine-tuned adapters on [HuggingFace](https://huggingface.co/xtuner). ## 📖 Introduction XTuner is a toolkit for efficiently fine-tuning LLM, developed by the [MMRazor](https://github.com/open-mmlab/mmrazor) and [MMDeploy](https://github.com/open-mmlab/mmdeploy) teams. - **Efficiency**: Support LLM fine-tuning on consumer-grade GPUs. The minimum GPU memory required for 7B LLM fine-tuning is only **8GB**, indicating that users can use nearly any GPU (even the free resource, *e.g.*, Colab) to fine-tune custom LLMs. -- **Versatile**: Support various **LLMs** ([InternLM](https://github.com/InternLM/InternLM), [Llama2](https://github.com/facebookresearch/llama), [ChatGLM2](https://huggingface.co/THUDM/chatglm2-6b), [Qwen](https://github.com/QwenLM/Qwen-7B), [Baichuan](https://github.com/baichuan-inc), ...), **datasets** ([MOSS_003_SFT](https://huggingface.co/datasets/fnlp/moss-003-sft-data), [Colorist](https://huggingface.co/datasets/burkelibbey/colors), [Code Alpaca](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K), [Arxiv GenTitle](https://github.com/WangRongsheng/ChatGenTitle), [Chinese Law](https://github.com/LiuHC0428/LAW-GPT), [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca), [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus), ...) and **algorithms** ([QLoRA](http://arxiv.org/abs/2305.14314), [LoRA](http://arxiv.org/abs/2106.09685)), allowing users to choose the most suitable solution for their requirements. +- **Versatile**: Support various **LLMs** ([InternLM](https://github.com/InternLM/InternLM), [Llama2](https://github.com/facebookresearch/llama), [ChatGLM2](https://huggingface.co/THUDM/chatglm2-6b), [Qwen](https://github.com/QwenLM/Qwen-7B), [Baichuan](https://github.com/baichuan-inc), ...), **datasets** ([MOSS_003_SFT](https://huggingface.co/datasets/fnlp/moss-003-sft-data), [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), [WizardLM](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k), [oasst1](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus), [Code Alpaca](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K), [Colorist](https://huggingface.co/datasets/burkelibbey/colors), ...) and **algorithms** ([QLoRA](http://arxiv.org/abs/2305.14314), [LoRA](http://arxiv.org/abs/2106.09685)), allowing users to choose the most suitable solution for their requirements. - **Compatibility**: Compatible with [DeepSpeed](https://github.com/microsoft/DeepSpeed) 🚀 and [HuggingFace](https://huggingface.co) 🤗 training pipeline, enabling effortless integration and utilization. ## 🌟 Demos @@ -68,15 +68,16 @@ XTuner is a toolkit for efficiently fine-tuning LLM, developed by the [MMRazor]( diff --git a/README_zh-CN.md b/README_zh-CN.md index 95e147fa8..6094676e7 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -14,14 +14,14 @@ ## 🎉 更新 -- **\[2023.08.XX\]** XTuner 正式发布！众多微调模型已上传至 [HuggingFace](https://huggingface.co/xtuner)！ +- **\[2023.08.30\]** XTuner 正式发布！众多微调模型已上传至 [HuggingFace](https://huggingface.co/xtuner)！ ## 📖 介绍 XTuner 是一个轻量级微调大语言模型的工具库，由 [MMRazor](https://github.com/open-mmlab/mmrazor) 和 [MMDeploy](https://github.com/open-mmlab/mmdeploy) 团队联合开发。 - **轻量级**: 支持在消费级显卡上微调大语言模型。对于 7B 参数量，微调所需的最小显存仅为 **8GB**，这使得用户可以使用几乎任何显卡（甚至免费资源，例如Colab）来微调获得自定义大语言模型助手。 -- **多样性**: 支持多种**大语言模型**（[InternLM](https://github.com/InternLM/InternLM)、[Llama2](https://github.com/facebookresearch/llama)、[ChatGLM2](https://huggingface.co/THUDM/chatglm2-6b)、[Qwen](https://github.com/QwenLM/Qwen-7B)、[Baichuan](https://github.com/baichuan-inc), ...），**数据集**（[MOSS_003_SFT](https://huggingface.co/datasets/fnlp/moss-003-sft-data)、[Colorist](https://huggingface.co/datasets/burkelibbey/colors)、[Code Alpaca](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K)、[Arxiv GenTitle](https://github.com/WangRongsheng/ChatGenTitle)、[Chinese Law](https://github.com/LiuHC0428/LAW-GPT)、[OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)、[Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)，...）和**微调算法**（[QLoRA](http://arxiv.org/abs/2305.14314)、[LoRA](http://arxiv.org/abs/2106.09685)），支撑用户根据自身具体需求选择合适的解决方案。 +- **多样性**: 支持多种**大语言模型**（[InternLM](https://github.com/InternLM/InternLM)、[Llama2](https://github.com/facebookresearch/llama)、[ChatGLM2](https://huggingface.co/THUDM/chatglm2-6b)、[Qwen](https://github.com/QwenLM/Qwen-7B)、[Baichuan](https://github.com/baichuan-inc), ...），**数据集**（[MOSS_003_SFT](https://huggingface.co/datasets/fnlp/moss-003-sft-data), [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), [WizardLM](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k), [oasst1](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus), [Code Alpaca](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K), [Colorist](https://huggingface.co/datasets/burkelibbey/colors), ...）和**微调算法**（[QLoRA](http://arxiv.org/abs/2305.14314)、[LoRA](http://arxiv.org/abs/2106.09685)），支撑用户根据自身具体需求选择合适的解决方案。 - **兼容性**: 兼容 [DeepSpeed](https://github.com/microsoft/DeepSpeed) 🚀 和 [HuggingFace](https://huggingface.co) 🤗 的训练流程，支撑用户无感式集成与使用。 ## 🌟 示例 @@ -68,15 +68,16 @@ XTuner 是一个轻量级微调大语言模型的工具库，由 [MMRazor](https