Instructions to use BAAI/EVA-CLIP-18B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/EVA-CLIP-18B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BAAI/EVA-CLIP-18B", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("BAAI/EVA-CLIP-18B", trust_remote_code=True) model = AutoModel.from_pretrained("BAAI/EVA-CLIP-18B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same
#1
by h420405961 - opened
Hello, I encountered an error while running the code from Huggingface_Version: RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same."