10.5. 调优¶

10.5.1. ms-swift¶

https://github.com/modelscope/swift
SWIFT支持300+ LLM和50+ MLLM（多模态大模型）的训练(预训练、微调、对齐)、推理、评测和部署。开发者可以直接将我们的框架应用到自己的Research和生产环境中，实现模型训练评测到应用的完整链路。我们除支持了PEFT提供的轻量训练方案外，也提供了一个完整的Adapters库以支持最新的训练技术，如NEFTune、LoRA+、LLaMA-PRO等，这个适配器库可以脱离训练脚本直接使用在自己的自定流程中。

10.5.2. LLaMA Factory¶

文档: https://llamafactory.readthedocs.io/zh-cn/latest/index.html
GitHub: https://github.com/hiyouga/LLaMA-Factory

Usage:

llamafactory-cli api -h: launch an OpenAI-style API server
llamafactory-cli chat -h: launch a chat interface in CLI
llamafactory-cli eval -h: evaluate models
llamafactory-cli export -h: merge LoRA adapters and export model
llamafactory-cli train -h: train models
llamafactory-cli webchat -h: launch a chat interface in Web UI
llamafactory-cli webui: launch LlamaBoard
llamafactory-cli version: show version info

uiWeb Lora调优示例: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
命令行 Lora调优示例: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing

10.5.3. FastChat¶

https://github.com/lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.