hi-todayis-jh/l1-exact-qwen3-1.7b-compression-bs32-n8-32k-t1-146103-rollouts download history

hi-todayis-jh/l1-exact-qwen3-1.7b-compression-bs32-n8-32k-t1-146103-rollouts is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 447 times (447 in the last 7 days), and 447 times in total. It ranks #36,302 among datasets by monthly downloads.

RL training rollouts l1_exact_Qwen3-1.7B_compression_n400to12000_bs32_n8_32k_1epoch One verified gzip JSONL shard per training step; 256 responses per shard. L1-Exact: MathVerify correctness after thinking without an EOS gate, plus the original linear target-length reward. Fixed targe

Open hi-todayis-jh/l1-exact-qwen3-1.7b-compression-bs32-n8-32k-t1-146103-rollouts on Hugging Face

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