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
License: apache-2.0Qwen2-VL-2B QLoRA — Amazon ML Challenge 2025 (Smart Product Pricing)
LoRA adapter fine-tuned with Unsloth on the Amazon ML Challenge 2025 dataset to predict product price (USD) from catalog text + product image.
- Base:
unsloth/Qwen2-VL-2B-Instruct-bnb-4bit(Apache-2.0) - LoRA: r=16, alpha=16, language/attention/mlp layers (vision frozen)
- Trained 1 epoch, ~74k examples, checkpoint @ step 4000 (val loss 0.908)
- Image size 336, fp16, batch 4 x grad-accum 4, lr 2e-4 cosine
Model provider
Vedant3907
Model tree
Base
unsloth/Qwen2-VL-2B-Instruct-bnb-4bit
Adapter
this model
Modalities
Input
Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information