Zero-Shot Image Classification
Transformers
Safetensors
MLX
siglip
vision
medical
radiology
dermatology
pathology
ophthalmology
chest-x-ray
Instructions to use mlx-community/medsiglip-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/medsiglip-448 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="mlx-community/medsiglip-448") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("mlx-community/medsiglip-448") model = AutoModelForZeroShotImageClassification.from_pretrained("mlx-community/medsiglip-448", device_map="auto") - MLX
How to use mlx-community/medsiglip-448 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/medsiglip-448 --local-dir medsiglip-448
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Update config.json
Browse files- config.json +0 -4
config.json
CHANGED
|
@@ -5,8 +5,6 @@
|
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"model_type": "siglip",
|
| 7 |
"text_config": {
|
| 8 |
-
"attention_dropout": 0.0,
|
| 9 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 10 |
"hidden_size": 1152,
|
| 11 |
"intermediate_size": 4304,
|
| 12 |
"layer_norm_eps": 1e-06,
|
|
@@ -20,8 +18,6 @@
|
|
| 20 |
"torch_dtype": "float32",
|
| 21 |
"transformers_version": "4.52.4",
|
| 22 |
"vision_config": {
|
| 23 |
-
"attention_dropout": 0.0,
|
| 24 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 25 |
"hidden_size": 1152,
|
| 26 |
"image_size": 448,
|
| 27 |
"intermediate_size": 4304,
|
|
|
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"model_type": "siglip",
|
| 7 |
"text_config": {
|
|
|
|
|
|
|
| 8 |
"hidden_size": 1152,
|
| 9 |
"intermediate_size": 4304,
|
| 10 |
"layer_norm_eps": 1e-06,
|
|
|
|
| 18 |
"torch_dtype": "float32",
|
| 19 |
"transformers_version": "4.52.4",
|
| 20 |
"vision_config": {
|
|
|
|
|
|
|
| 21 |
"hidden_size": 1152,
|
| 22 |
"image_size": 448,
|
| 23 |
"intermediate_size": 4304,
|