Instructions to use tanganke/clip-vit-base-patch32_cifar10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tanganke/clip-vit-base-patch32_cifar10 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="tanganke/clip-vit-base-patch32_cifar10")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("tanganke/clip-vit-base-patch32_cifar10") model = AutoModel.from_pretrained("tanganke/clip-vit-base-patch32_cifar10", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from tanganke/clip-vit-base-patch32_cifar10: direct link, hf CLI and curl.
- Browser
- Download file 856 Bytes
-
https://huggingface.co/tanganke/clip-vit-base-patch32_cifar10/resolve/main/README.md
- Command line
-
hf download hf://tanganke/clip-vit-base-patch32_cifar10/README.md
-
curl -L -o README.md https://huggingface.co/tanganke/clip-vit-base-patch32_cifar10/resolve/main/README.md
856 Bytes
metadata
base_model:
- openai/clip-vit-base-patch32
datasets:
- cifar10
metrics:
- accuracy
Model Card
Model Details
- Architecture: ViT-Base with patch size 32
- Training Data: cifar10
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: 0.8982999920845032
- fine-tuned: 0.9759999513626099
Usage
load vision model
from transformers import CLIPVisionModel
vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_cifar10')
substitute the vision encoder of clip
from transformers import CLIPModel
clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
clip_model.vision_model.load_state_dict(vision_model.vision_model.state_dict())