Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

Metrics

MetricValue
Baseline refusal95.8%
Edited refusal12.4%
Harmless KL0.133
KL target0.060
Preserve rank4
Preserve sourcenone
Direction layer24
Elapsed522.6 sec

Reproduction

bash

apostate ablate --model google/gemma-4-E4B-it --out C:\Users\Levit\OneDrive\Desktop\apostatehfmodels\gemma-4-e4b-it-apostate --resume --activation-cache-dir C:\Users\Levit\OneDrive\Desktop\apostatehfmodels\gemma-4-e4b-it-apostate\activation_cache

Measurement

fieldvalue
edit typeweight projection
refusal judgeclassifier + hard refusal guard
preservation metricharmless kl

Model provider

heterodoxin

Model tree

Base

google/gemma-4-E4B-it

Fine-tuned

this model

Modalities

Input

Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today