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
License: apache-2.0Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | 18.61 |
| attn.o_proj.max_weight | 1.46 |
| attn.o_proj.max_weight_position | 21.20 |
| attn.o_proj.min_weight | 1.04 |
| attn.o_proj.min_weight_distance | 17.65 |
| mlp.down_proj.max_weight | 0.82 |
| mlp.down_proj.max_weight_position | 26.83 |
| mlp.down_proj.min_weight | 0.12 |
| mlp.down_proj.min_weight_distance | 6.62 |
Performance
| Metric | This model | Original model (sulpikar2/Qwenpus3.5-9B-exp) |
|---|---|---|
| KL divergence | 0.0031 | 0 (by definition) |
| Refusals | 3/100 | 81/100 |
Model provider
sulpikar2
Model tree
Base
this model
Modalities
Input
Video, Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information