Inference Llama 2 in one file of pure C
Emscripten: An LLVM-to-WebAssembly Compiler
Distribute and run LLMs with a single file
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon
A high-performance ML model serving framework, offers dynamic batching
Tools like web browser, computer access and code runner for LLMs
Ongoing research training transformer models at scale
llama.go is like llama.cpp in pure Golang
Codes for "Chameleon: Plug-and-Play Compositional Reasoning