Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
Features
- Python 3.8+ and PyTorch 1.13.1+
- Transformers, Datasets, Accelerate, PEFT and TRL
- jieba, rouge-chinese and nltk (used at evaluation)
- gradio and matplotlib (used in web_demo.py)
- uvicorn, fastapi and sse-starlette (used in api_demo.py)
- Currently the web UI only supports training on a single GPU
Categories
Large Language Models (LLM)License
Apache License V2.0Follow LLaMA Efficient Tuning
Other Useful Business Software
Fully Managed MySQL, PostgreSQL, and SQL Server
Cloud SQL handles your database ops end to end, so you can focus on your app.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of LLaMA Efficient Tuning!