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
CADmium CAD GRPO 9B Adapter
This repository contains the final GRPO LoRA adapter from the CADmium 9B fine-tuning pipeline.
Training stack:
- Base model:
Qwen/Qwen3.5-9B - SFT adapter:
/checkpoints/sft_final_9b - GRPO adapter:
/checkpoints/grpo_final_9b
For direct inference, prefer the merged model repo if available. This adapter repo is useful for provenance, inspection, and continued fine-tuning.
Model provider
gaurav-tyagi
Model tree
Base
Qwen/Qwen3.5-9B
Adapter
this model
Modalities
Input
Video, Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information