bookxd/jmh-grpo-replication-data download history

bookxd/jmh-grpo-replication-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 299 times (299 in the last 7 days), and 299 times in total. It ranks #49,244 among datasets by monthly downloads.

JMH-Bench GRPO replication data Data for replicating the BSc thesis Reinforcement Learning with Verifiable Execution Rewards for Synthesizing Regression-Detecting Microbenchmarks. The code is in the replication repository RL4JMH-thesis-submission. The trained models are run 9 (evaluat

Open bookxd/jmh-grpo-replication-data on Hugging Face

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