Hugging Face's logo

UnfaithRL
/
OLMo-2-0425-1B-hybrid_accuracy_hint_reward-2048

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-2048
File size: 135 Bytes
c83ee3c
 
 
1
2
3
4
version https://git-lfs.github.com/spec/v1
oid sha256:67c908a14c9f6c6f680e0904bd6caa3a30b283a9f4144045e7a02d40977b2b77
size 4983360992