K2-65B: the first reproducible LLM to outperform Llama 2 70Btwitter.com1 ポイント·投稿者 sunandcoffee·2 年前·0 コメント
LLM360 – transparent LLMs with intermediate checkpoints and data bucketstwitter.com4 ポイント·投稿者 sunandcoffee·3 年前·0 コメント
sunandcoffee·2 年前·議論what are you thoughts on projects like these: https://www.llm360.ai/seems like they make everything available.
sunandcoffee·3 年前·議論Looks like the model is slightly worse on language ability but better on coding ability. This might be a good model for trying agents.
seems like they make everything available.