Hugging Face
Models
Datasets
Spaces
Buckets
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
aytsrndl
/
constitutional-classifiers-repro
Like
0
ml-intern
ai-safety
constitutional-classifiers
arxiv:
2501.18837
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
constitutional-classifiers-repro
/
scripts
29.7 kB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
aytsrndl
output classifier trainer (value head, omega ramp)
808f43d
verified
1 day ago
build_dataset.py
8.76 kB
dataset builder: seeds + vLLM augmentation
1 day ago
evaluate.py
10.1 kB
calibration + red-team eval with rubric judge
1 day ago
train_input_classifier.py
3.82 kB
input classifier trainer (TRL SFT, NTP verdict)
1 day ago
train_output_classifier.py
6.98 kB
output classifier trainer (value head, omega ramp)
1 day ago