lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909-completion download history
lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909-completion is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 8,128 times (827 in the last 7 days), and 8,128 times in total. It ranks #3,704 among datasets by monthly downloads.
Matched no-conftest RLVR study 20260909-completion Lossless research records, grouped by model and trajectory type. Only the listed configurations have published records. Canary diagnostics are excluded from study estimates; run status in provenance distinguishes retired diagnostics f
Models trained on rlvr-reward-hacking-scale-no-conftest-20260909-completion
4 models list it as training data.
- lucabaroni/qwen38-27b-rlvr-no-conftest-20260909-completion 52 downloads in 30 days
- lucabaroni/nemotron3-nano-30b-rlvr-no-conftest-20260909-completion 37 downloads in 30 days
- lucabaroni/nemotron3-120b-rlvr-no-conftest-20260909-completion 35 downloads in 30 days
- lucabaroni/gpt-oss-20b-rlvr-no-conftest-20260909-completion 25 downloads in 30 days
Spaces using rlvr-reward-hacking-scale-no-conftest-20260909-completion
- Model Pulse 31 likes
Open lucabaroni/rlvr-reward-hacking-scale-no-conftest-20260909-completion on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.