Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
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
License: mitcurbcheck v4 — QLoRA adapter for Qwen2.5-VL-3B
LoRA adapter that teaches Qwen2.5-VL-3B to read San Francisco parking-sign stacks into structured rules (kind, days, hours, limits, permits, week-of-month). Pair with the deterministic resolver in https://github.com/shubhamgoel27/curbcheck to decide whether you can park at a given time.
- Base: Qwen/Qwen2.5-VL-3B-Instruct
- Method: QLoRA (r=16) on the language layers; vision tower frozen
- Synthetic benchmark: read F1 0.98, reasoning 0.82
Model provider
shubhamgoel27
Model tree
Base
Qwen/Qwen2.5-VL-3B-Instruct
Adapter
this model
Modalities
Input
Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information