Explore the detailed documentation and usage guides of all open source projects in the Large Language Models category.
The pure C implementation of the Llama 2 model developed by Andrej Karpathy, optimized for efficient inference.
A self-hosted, community-driven, and locally-focused OpenAI alternative. No GPU required, run language models and embeddings on CPU.
A framework for running, setting up, and using large language models on your local machine.
Interact with your documents privately using local LLMs, without the need for internet connection.