Get up and running with Llama 2 and other large language models
Port of Facebook's LLaMA model in C/C++
Distribute and run LLMs with a single file
Locally run an Instruction-Tuned Chat-Style LLM
Integrate cutting-edge LLM technology quickly and easily into your app
Self-hosted, community-driven, local OpenAI compatible API
LLMs for your CLI
Python bindings for the Transformer models implemented in C/C++
C#/.NET binding of llama.cpp, including LLaMa/GPT model inference
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
llama.go is like llama.cpp in pure Golang
Leveraging BERT and c-TF-IDF to create easily interpretable topics
Ongoing research training transformer models at scale
Vector database plugin for Postgres, written in Rust
An ecosystem of Rust libraries for working with large language models
Implements a reference architecture for creating information systems