Image Classification
Transformers
LiteRT
ONNX
Safetensors
English
siglip
zero-shot-image-classification
vision
cervical-cancer
diagnosis
Instructions to use KhanyiTapiwa00/medsiglip-diagnosis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KhanyiTapiwa00/medsiglip-diagnosis with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="KhanyiTapiwa00/medsiglip-diagnosis") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("KhanyiTapiwa00/medsiglip-diagnosis") model = AutoModelForZeroShotImageClassification.from_pretrained("KhanyiTapiwa00/medsiglip-diagnosis", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "dtype": "float32", | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "max_position_embeddings": 64, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "projection_size": 1152, | |
| "vocab_size": 32000 | |
| }, | |
| "transformers_version": "4.56.1", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 448, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14 | |
| } | |
| } | |