mahwizzzz/hh-rlhf-urdu download history
mahwizzzz/hh-rlhf-urdu is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 51 times (12 in the last 7 days), and 208 times in total. It ranks #260,284 among datasets by monthly downloads.
HH-RLHF Urdu Urdu translation of the Anthropic HH-RLHF preference data, for Urdu reward-model and policy-training research. The only split recorded below is train (11,225 examples). A held-out split is not defined in this card. Purpose Provide chosen and rejected conver
Models trained on hh-rlhf-urdu
1 models list it as training data.
- mahwizzzz/Qalb-1.0-8B-DPO 39 downloads in 30 days
Open mahwizzzz/hh-rlhf-urdu on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.