Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed. [Moved to: https://github.com/Lightning-AI/litgpt]
Why do you think that https://github.com/ggerganov/llama.cpp is a good alternative to lit-gpt