Hugging Face's logo

anonym371
/
dose-response-c4

Text-to-Image
diffusion
safety
dose-response
Model card Files
xet
 Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Dose-Response C4: Original proportion (~1.21% unsafe), 1M scale

Part of a dose-response experiment studying how unsafe training data fraction affects text-to-image model safety.

Architecture PRX-1.2B
Condition C4 — Original proportion (~1.21% unsafe), 1M scale
Training set 1M images
Downscaled to 1M images while preserving the original ~1.21% unsafe proportion (12K unsafe, 988K safe).

Files

  • denoiser.pt — Consolidated checkpoint (EMA weights)
  • distributed/ — FSDP distributed shards
  • config.yaml — Training configuration
Downloads last month
16
Inference Providers NEW
Text-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for anonym371/dose-response-c4

Finetunes
1 model

Datasets used to train anonym371/dose-response-c4

Collection including anonym371/dose-response-c4