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.

GitHub
6k stars
67 watching
518 forks
Language: Python
last commit: 29 days ago
Linked from 2 awesome lists


Backlinks from these awesome lists: