od2961/illusion-of-reasoning-main-traces download history

od2961/illusion-of-reasoning-main-traces is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 53 times (14 in the last 7 days), and 1,377 times in total. It ranks #178,362 among datasets by monthly downloads.

Illusion of Reasoning - Main Traces Overview This dataset contains reasoning traces from GRPO models across multiple tasks and temperatures. It includes: GRPO-1.5B on math, crosswords, and carpark (temps: 0, 0.05, 0.3, 0.7) GRPO-7B on math (temps: 0, 0.05, 0.3, 0.7) GRPO-Llama

Open od2961/illusion-of-reasoning-main-traces on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.