Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
Reward Misspecification Degrades CoT Monitorability
LoRA checkpoints of models GRPO-trained on a true or misspecified reward (coding, judge, length), with their training datasets.
Reward Misspecification Degrades CoT Monitorability
LoRA checkpoints of models GRPO-trained on a true or misspecified reward (coding, judge, length), with their training datasets.