Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AlignmentResearch
/
obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-deception_probe
like
0
Follow
FAR AI
57
PEFT
deception-detection
rlvr
alignment-research
obfuscation-atlas
lora
model-type:honest
arxiv:
2602.15515
License:
mit
Model card
Files
Files and versions
xet
Community
Use this model
main
obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-deception_probe
1.23 GB
1 contributor
History:
4 commits
taufeeque
Upload README.md with huggingface_hub
1ff1bfe
verified
17 days ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
21 days ago
README.md
Safe
3.28 kB
Upload README.md with huggingface_hub
17 days ago
adapter_config.json
Safe
972 Bytes
Upload folder using huggingface_hub
21 days ago
adapter_model.bin
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
What is a pickle import?
1.19 GB
xet
Upload folder using huggingface_hub
21 days ago
added_tokens.json
Safe
35 Bytes
Upload folder using huggingface_hub
21 days ago
chat_template.jinja
Safe
1.53 kB
Upload folder using huggingface_hub
21 days ago
special_tokens_map.json
Safe
662 Bytes
Upload folder using huggingface_hub
21 days ago
tokenizer.json
Safe
33.4 MB
xet
Upload folder using huggingface_hub
21 days ago
tokenizer.model
Safe
4.69 MB
xet
Upload folder using huggingface_hub
21 days ago
tokenizer_config.json
Safe
1.16 MB
Upload folder using huggingface_hub
21 days ago
