Alibaba's Apache 2.0 LLM in sizes from small to frontier scale
Permissive open LLaMA reproduction in 3B, 7B, and 13B parameters
Allen AI research LLM with public weights and open training code
Compact 1.1B LLaMA model trained on 3 trillion tokens
Full transparency LLM: open weights, training code, and data
Self-hosted vector database for AI similarity search and RAG
EleutherAI's framework for training LLMs at research scale
