YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
LPCVC CPU-Only CLIP Baseline
This model is a submission-first binary detector for LPCVC.
- Backbone:
openai/clip-vit-base-patch32 - Scope: image tower only
- Fine-tune scope: frozen CLIP vision backbone + linear classifier head
- Labels:
Real,AI-Generated - Explanations: not learned; later stage1/stage2 formatting is deterministic post-processing
Load
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("YOUR_REPO", trust_remote_code=True)
model = AutoModelForImageClassification.from_pretrained("YOUR_REPO", trust_remote_code=True)
Boundary
This export is not the final Qualcomm/QNN submission artifact. It is the simplified upstream detector model that will be bridged later.
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support