Instructions to use Ozantsk/biomedclip-rocov2-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use Ozantsk/biomedclip-rocov2-finetuned with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Ozantsk/biomedclip-rocov2-finetuned') tokenizer = open_clip.get_tokenizer('hf-hub:Ozantsk/biomedclip-rocov2-finetuned') - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224", | |
| "dataset": "eltorio/ROCOv2-radiology", | |
| "epoch": 4, | |
| "global_step": 3748, | |
| "learning_rate": 1e-05, | |
| "epochs": 4, | |
| "batch_size": 16, | |
| "grad_accum_steps": 4, | |
| "effective_batch_size": 64, | |
| "weight_decay": 0.02, | |
| "warmup_ratio": 0.05, | |
| "context_length": 256 | |
| } |