MNoorFawi/curlora
The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.
3 best points · 0 comments · 2 Hacker News posts · 53 GitHub stars · View on GitHub
Hacker News discussions
- Show HN: Fine-tune LLMs without catastrophic forgetting with CURLoRA approach (3 points, 0 comments, by mnoorfawi, 2024-07-21)
- Continually fine-tune large language models without catastrophic forgetting (1 points, 0 comments, by amrzxc, 2024-07-18)