Hugging Face's logo

UnfaithRL
/
OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512

Reinforcement Learning
Transformers
Safetensors
olmo2
text-generation
rlvr
rl-zero
chain-of-thought
faithfulness
reward-hacking
cue-injection
unfaithrl
Model card Files
xet
 Community
OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512
File size: 135 Bytes
f5ecfd5
 
 
1
2
3
4
version https://git-lfs.github.com/spec/v1
oid sha256:69ee540359e5842bf58ea230d189d1ef8dc82aab5f52165c81a1acd57f4014d6
size 4983360992