INSAIT-Institute/Aletheia-DPO download history
INSAIT-Institute/Aletheia-DPO is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 20 times (3 in the last 7 days), and 80 times in total. It ranks #478,684 among datasets by monthly downloads.
[📖 Paper] [💻 Code] [🤗 Models & Datasets] Aletheia: What Makes RLVR For Code Verifiers Tick? Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training. However, their adoption in code generation has la
Models trained on Aletheia-DPO
3 models list it as training data.
- INSAIT-Institute/DPO-Think-1.5B 16 downloads in 30 days
- INSAIT-Institute/DPO-Think-7B 15 downloads in 30 days
- INSAIT-Institute/DPO-Think-14B 9 downloads in 30 days
Open INSAIT-Institute/Aletheia-DPO on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.