YAML Metadata Warning: empty or missing yaml metadata in repo card
Check out the documentation for more information.
MiniCLIP model
This repository contains a fine-tuned MiniCLIP-style model saved as a PyTorch .pt file.
Model details
- Vision encoder: google/vit-base-patch16-224
- Text encoder: roberta-base
Usage
Download model.pt and load with torch.load(...) into your MiniCLIP model wrapper defined in the project, or use the provided code to reconstruct the model architecture before loading weights.
Uploaded from local training
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support