Lightning-AI/lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

158 best points · 52 comments · 1 Hacker News post · 6,083 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: A fully open-source (Apache 2.0)implementation of llama (158 points, 52 comments, by osurits, 2023-03-28)