1
RedPajama: Reproduction of LLaMA with friendly license
RedPajama launches to build fully open-source leading language models, starting by reproducing LLaMA's training dataset of over 1.2 trillion tokens.
Build what's next on the AI Native Cloud. Full-stack AI platform for inference, fine-tuning, and GPU clusters — powered by cutting-edge research.
Visit together.xyz → RSS feedOn Hacker News Nov 2022 – May 2023
RedPajama launches to build fully open-source leading language models, starting by reproducing LLaMA's training dataset of over 1.2 trillion tokens.
Together releases the RedPajama-INCITE 3B and 7B model family, including base, instruction-tuned, and chat versions, with the 3B model running on an RTX 2070.