Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
HenDav
/
value-steer-safety-head
like
0
value-steer
vllm
safety
alignment
value-filtered-decoding
inference-time-intervention
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
value-steer-safety-head
134 MB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
HenDav
Upload README.md with huggingface_hub
8331bdc
verified
30 days ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
README.md
Safe
3.83 kB
Upload README.md with huggingface_hub
30 days ago
eval_results.md
Safe
2.07 kB
Canonical decode-matched safety value head (Mistral-7B, 17k prompts x4); held-out eval + model card
about 1 month ago
value_head.bin
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
134 MB
xet
Canonical decode-matched safety value head (Mistral-7B, 17k prompts x4); held-out eval + model card
about 1 month ago
value_head.bin.meta.json
Safe
385 Bytes
Upload value_head.bin.meta.json with huggingface_hub
30 days ago
