[assets] update readme (#8110)

This commit is contained in:
hoshi-hiyouga
2025-05-20 02:44:18 +08:00
committed by GitHub
parent 9b5baa97f0
commit c2f6f2fa77
3 changed files with 47 additions and 1258 deletions

View File

@@ -5,7 +5,7 @@
[![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors)
[![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml)
[![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
[![Citation](https://img.shields.io/badge/citation-447-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
[![Citation](https://img.shields.io/badge/citation-476-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
[![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
[![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
@@ -18,16 +18,27 @@
[![Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)
[![SageMaker](https://img.shields.io/badge/SageMaker-Open%20in%20AWS-blue)](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)
<h3 align="center">
使用零代码<a href="#快速开始">命令行</a><a href="#llama-board-可视化微调由-gradio-驱动">Web UI</a> 轻松微调百余种大模型
</h3>
### 获得[亚马逊](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)、[英伟达](https://developer.nvidia.cn/rtx/ai-toolkit)、[阿里云](https://help.aliyun.com/zh/pai/use-cases/fine-tune-a-llama-3-model-with-llama-factory)等的应用。
<p align="center">
<picture>
<img alt="Github trend" src="https://trendshift.io/api/badge/repositories/4535">
</picture>
</p>
<div align="center" markdown="1">
### 赞助商 ❤️
<a href="https://warp.dev/llama-factory">
<img alt="Warp sponsorship" width="400" src="https://github.com/user-attachments/assets/ab8dd143-b0fd-4904-bdc5-dd7ecac94eae">
</a>
#### [Warp面向开发者的智能终端](https://warp.dev/llama-factory)
[适用于 MacOS、Linux 和 Windows](https://warp.dev/llama-factory)
----
### 使用零代码[命令行](#快速开始)与 [Web UI](#llama-board-可视化微调由-gradio-驱动) 轻松微调百余种大模型
![GitHub Trend](https://trendshift.io/api/badge/repositories/4535)
</div>
👋 加入我们的[微信群](assets/wechat.jpg)或 [NPU 用户群](assets/wechat_npu.jpg)。
@@ -54,7 +65,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
## 目录
- [项目特色](#项目特色)
- [性能指标](#性能指标)
- [官方博客](#官方博客)
- [更新日志](#更新日志)
- [模型](#模型)
- [训练方法](#训练方法)
@@ -94,18 +105,17 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
| Day 0 | Qwen3 / Qwen2.5-VL / Gemma 3 / InternLM 3 / MiniCPM-o-2.6 |
| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4 |
## 性能指标
## 官方博客
与 ChatGLM 官方的 [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning) 微调相比LLaMA Factory 的 LoRA 微调提供了 **3.7 倍**的加速比,同时在广告文案生成任务上取得了更高的 Rouge 分数。结合 4 比特量化技术LLaMA Factory 的 QLoRA 微调进一步降低了 GPU 显存消耗。
- [通过亚马逊 SageMaker HyperPod 上的 LLaMA-Factory 增强多模态模型银行文档的视觉信息提取](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/)(英文)
- [Easy Dataset × LLaMA Factory: 让大模型高效学习领域知识](https://buaa-act.feishu.cn/wiki/KY9xwTGs1iqHrRkjXBwcZP9WnL9)(中文)
- [LLaMA Factory微调DeepSeek-R1-Distill-Qwen-7B模型实现新闻标题分类器](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b)(中文)
![benchmark](assets/benchmark.svg)
<details><summary>全部博客</summary>
<details><summary>变量定义</summary>
- **Training Speed**: 训练阶段每秒处理的样本数量。(批处理大小=4截断长度=1024
- **Rouge Score**: [广告文案生成](https://aclanthology.org/D19-1321.pdf)任务验证集上的 Rouge-2 分数。(批处理大小=4截断长度=1024
- **GPU Memory**: 4 比特量化训练的 GPU 显存峰值。(批处理大小=1截断长度=1024
- 我们在 ChatGLM 的 P-Tuning 中采用 `pre_seq_len=128`,在 LLaMA Factory 的 LoRA 微调中采用 `lora_rank=32`
- [基于 Amazon SageMaker 和 LLaMA-Factory 打造一站式无代码模型微调部署平台 Model Hub](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)(中文)
- [LLaMA Factory多模态微调实践微调Qwen2-VL构建文旅大模型](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)(中文)
- [LLaMA Factory微调LLaMA3模型实现角色扮演](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)(中文
</details>