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: 134 Bytes
c83ee3c
 
 
1
2
3
4
version https://git-lfs.github.com/spec/v1
oid sha256:ec8aa99f67795da5c5cc9032b46328d09c7d63ace203b64861234633f7ca82f7
size 956326560