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
aisa-group
/
training_against_probes
Like
4
Follow
AI Safety and Alignment Group at the ELLIS Institute Tübingen and MPI-IS
16
PEFT
Safetensors
lora
alignment
safety
honesty
linear-probes
interpretability
arxiv:
2609.38645
License:
base-model-licenses
Model card
Files
Files and versions
xet
Community
Deploy
Copy to bucket
Use this model
Instructions to use aisa-group/training_against_probes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
PEFT
How to use aisa-group/training_against_probes with PEFT:
Task type is invalid.
Notebooks
Google Colab
Kaggle
main
training_against_probes
85.6 GB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
lenalibon
publish checkpoints and probes
690ddaa
10 days ago
harmfulness
publish checkpoints and probes
10 days ago
honesty
publish checkpoints and probes
10 days ago
.gitattributes
Safe
1.52 kB
publish checkpoints and probes
10 days ago
LICENSE.md
Safe
615 Bytes
publish checkpoints and probes
10 days ago
README.md
Safe
6.97 kB
publish checkpoints and probes
10 days ago
manifest.json
Safe
3.87 kB
publish checkpoints and probes
10 days ago
