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.

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

SFT fine-tuned from base C4 using Alchemist (3,350 images) for 20K steps.


Base model	dose-response-c4
Condition	C4 — Original proportion (~1.21% unsafe), 1M scale
SFT dataset	Alchemist (3,350 images)

Base model

Finetuned

(1)

this model