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
interpretable-finetuning
/
gemma-clean
Like
0
Follow
Interpretable Finetuning
2
Text Generation
PEFT
Safetensors
lora
topk-lora
control
interpretability
ai-safety
gemma2
License:
gemma
Model card
Files
Files and versions
xet
Community
Deploy
Copy to bucket
new
Use this model
Instructions to use interpretable-finetuning/gemma-clean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
PEFT
How to use interpretable-finetuning/gemma-clean with PEFT:
Task type is invalid.
Notebooks
Google Colab
Kaggle
main
gemma-clean
2.4 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
keramarek
Add model card
9fd0a25
verified
1 day ago
all
Add all family, no-poison control (r=64, k=8, seeds 42-46)
1 day ago
l1523
Add l1523 family, no-poison control (r=64, k=8, seeds 42-46)
1 day ago
l19
Add l19 family, no-poison control (r=64, k=8, seeds 42-46)
1 day ago
.gitattributes
Safe
1.52 kB
initial commit
1 day ago
README.md
8.98 kB
Add model card
1 day ago
clean_index.json
4.95 kB
Add clean_index.json (dataset facts, steps and trigger probes per adapter)
1 day ago
