About
An open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
Features
- Fine-tuned from LLaMA 13B on 70K ShareGPT conversations
- Trained in one week using 8 A100 GPUs with PyTorch FSDP
- Supports multi-turn dialogue with context retention
- Compatible with quantization (e.g., 4-bit) for efficient local inference
- Web demo provided by LMSYS for immediate testing
Links
Categories
Reviews
0
Write a Review
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.