Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
Metrics
| Metric | Value |
|---|---|
| Baseline refusal | 95.8% |
| Edited refusal | 3.8% |
| Refusal metric | classifier + weak guard |
| Harmless KL | 0.149 |
| KL target | 0.300 |
| Preserve rank | 8 |
| Preserve source | harmless |
| Direction layer | 25 |
| Elapsed | 1330.6 sec |
Measurement
| field | value |
|---|---|
| edit type | weight projection |
| refusal judge | classifier + weak guard |
| preservation metric | harmless kl |
Model provider
Spaceballs
Model tree
Base
google/gemma-4-E4B-it
Fine-tuned
this model
Modalities
Input
Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information