penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B download history

penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B is an 8.2B-parameter reinforcement learning model by penfever. In the last 30 days it was downloaded 10 times (1 in the last 7 days), and 334 times in total.

It ranks #800,028 on the Hub by monthly downloads and #15,023 among reinforcement learning models.

It has 0 likes.

It is a fine-tune of laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink.

Open penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B on Hugging Face

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