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.
Repository Index
97,836 visible repositories in the index
1–6 of 6 · Most stars
:blue_book: A curated list of awesome open source or open source licensed documents, guides, books.
Rust library for OpenAI
- openai
- rust
A 24bit colorscheme for Vim, Airline and Lightline
- vim
- theme
- colorscheme
- lightline
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
MicroPython driver for the ADS1256/ADS1255 24bit ADC.