K2-65B: the first reproducible LLM to outperform Llama 2 70Btwitter.com1 points·by sunandcoffee·2 years ago·0 comments
CrystalChat – 7B model from LLM360 beating Mistraltwitter.com3 points·by sunandcoffee·3 years ago·2 comments
LLM360 – transparent LLMs with intermediate checkpoints and data bucketstwitter.com4 points·by sunandcoffee·3 years ago·0 comments
sunandcoffee·2 years ago·discusswhat are you thoughts on projects like these: https://www.llm360.ai/seems like they make everything available.
sunandcoffee·3 years ago·discussLooks 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.