Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Container
Run this model inference with full control and performance in your environment.
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 | 66.7% |
| Edited refusal | 61.0% |
| Refusal metric | classifier + weak guard |
| Harmless KL | 0.305 |
| KL target | 0.300 |
| Preserve rank | 8 |
| Preserve source | harmless |
| Direction layer | 28 |
| Elapsed | 963.3 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-3-12b-it
Fine-tuned
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information