Hugging Face's logo

AlignmentResearch
/
obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed3-mbpp_probe

PEFT
deception-detection
rlvr
alignment-research
obfuscation-atlas
lora
model-type:honest
Model card Files
xet
 Community
obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed3-mbpp_probe
File size: 134 Bytes
b179402
 
 
1
2
3
4
version https://git-lfs.github.com/spec/v1
oid sha256:feb8409ddb8a5368ec9cc2c1bdbb79fb65a6e5c4ddffd9e9fd5a41707cd0cb2f
size 671251043