Downloads · 30 days
13K
55% of all-time downloads
clip-vit-large-patch14_dtd
tanganke/clip-vit-large-patch14_dtd
clip-vit-large-patch14_dtd is a feature extraction model from tanganke. Use it when you need embeddings to search or compare text. It is set up for transformers.
- Architecture: ViT-Large with patch size 14 - Training Data: DTD dataset
All-time downloads
23.5K
Public
Parameters
303M
1.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- clip_vision_model
- Access
- Public
- Created
- Apr 29, 2024
- Updated
- Apr 29, 2024
- SHA
- c55d192f
Base models
Datasets
Model card
From the Hugging Face model README
Model Card
Model Details
- Architecture: ViT-Large with patch size 14
- Training Data: DTD dataset
Training Details
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32). Only the vision encoder is fine-tuned.
Evaluation Results
- pre-trained: 0.554787278175354
- fine-tuned: 0.8547872304916382
- Task
- Feature Extraction
- Library
- transformers
- Type
- clip_vision_model
- Created
- Apr 29, 2024
- Updated
- Apr 29, 2024