Skip Navigation

Unsloth: 80% faster 50% less memory LLM finetuning

github.com

GitHub - unslothai/unsloth: 80% faster 50% less memory LLM finetuning

Hacker News @lemmy.smeargle.fans

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning

1 comments