UnfaithRL/Qwen2.5-0.5B-hybrid_accuracy_hint_reward-1024 download history

UnfaithRL/Qwen2.5-0.5B-hybrid_accuracy_hint_reward-1024 is a 494M-parameter reinforcement learning model by UnfaithRL. In the last 30 days it was downloaded 17 times (5 in the last 7 days), and 55 times in total.

It ranks #477,746 on the Hub by monthly downloads and #9,825 among reinforcement learning models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen2.5-0.5B.

Open UnfaithRL/Qwen2.5-0.5B-hybrid_accuracy_hint_reward-1024 on Hugging Face

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