kuleshov-group/llmtune

Finetuning Large Language Models on One Consumer GPU in 2 Bits

3 best points · 0 comments · 1 Hacker News post · 728 GitHub stars · View on GitHub

Hacker News discussions

• LLMTune: 4-Bit finetuning of 65B LLAMA models on a single consumer GPU (3 points, 0 comments, by volodia, 2023-05-14)