Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
AlignmentResearch
/
obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed1-mbpp_probe
like
0
Follow
FAR AI
64
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-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed1-mbpp_probe
689 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
taufeeque
Upload README.md with huggingface_hub
d2645d1
verified
2 months ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
2 months ago
README.md
Safe
3.33 kB
Upload README.md with huggingface_hub
2 months ago
adapter_config.json
Safe
948 Bytes
Upload folder using huggingface_hub
2 months ago
adapter_model.bin
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
What is a pickle import?
671 MB
xet
Upload folder using huggingface_hub
2 months ago
chat_template.jinja
Safe
389 Bytes
Upload folder using huggingface_hub
2 months ago
special_tokens_map.json
Safe
343 Bytes
Upload folder using huggingface_hub
2 months ago
tokenizer.json
Safe
17.2 MB
xet
Upload folder using huggingface_hub
2 months ago
tokenizer_config.json
Safe
50.6 kB
Upload folder using huggingface_hub
2 months ago
