openlm-research/open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

484 best points · 180 comments · 4 Hacker News posts · 7,518 GitHub stars · View on GitHub

Hacker News discussions

• OpenLLaMA: An Open Reproduction of LLaMA (484 points, 180 comments, by sadiq, 2023-05-03)
• OpenLLaMA: An Open Reproduction of LLaMA (4 points, 0 comments, by Jimmc414, 2023-05-02)
• OpenLLaMA to train beyond 1T tokens (2 points, 0 comments, by tosh, 2023-06-07)
• OpenLLaMA: Tokenizer Ignoring Multiple Spaces (1 points, 0 comments, by tosh, 2023-06-08)