Image Classification
Transformers
Safetensors
siglip2_hier_doc
feature-extraction
siglip2
document-classification
hierarchical
multi-task
custom_code
Instructions to use ekacare/med-doc-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ekacare/med-doc-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ekacare/med-doc-classifier", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ekacare/med-doc-classifier", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
transformers>=5.6.0 floor (older silently random-inits the vision tower); add torchvision
Browse files- requirements.txt +2 -1
requirements.txt
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
torch>=2.7.0
|
| 2 |
-
transformers
|
|
|
|
| 3 |
pillow
|
| 4 |
# Optional — only needed for int8/int4 quantized loading (runs on CPU and GPU):
|
| 5 |
optimum-quanto>=0.2.6
|
|
|
|
| 1 |
torch>=2.7.0
|
| 2 |
+
torchvision # required by AutoImageProcessor on transformers 5.x
|
| 3 |
+
transformers>=5.6.0 # earlier versions silently random-init the vision tower (see modeling file guard)
|
| 4 |
pillow
|
| 5 |
# Optional — only needed for int8/int4 quantized loading (runs on CPU and GPU):
|
| 6 |
optimum-quanto>=0.2.6
|