☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to Technology@lemmygrad.ml • 5 months agoBy using the same techniques Google used to solve Go (MTCS and backprop), Llama8B gets 96.7% on math benchmark GSM8K. That’s better than GPT-4, Claude and Gemini, with 200x less parameters!external-linkmessage-square0 fedilinkarrow-up118file-textcross-posted to: machinelearning@lemmy.ml
arrow-up118external-linkBy using the same techniques Google used to solve Go (MTCS and backprop), Llama8B gets 96.7% on math benchmark GSM8K. That’s better than GPT-4, Claude and Gemini, with 200x less parameters!☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to Technology@lemmygrad.ml • 5 months agomessage-square0 Commentsfedilinkfile-textcross-posted to: machinelearning@lemmy.ml
