Zero-Shot Image Classification
Transformers
Safetensors
flexict
feature-extraction
medical-imaging
ct
vision-language
custom_code
Instructions to use ricklisz123/FlexiCT-3D-VLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ricklisz123/FlexiCT-3D-VLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="ricklisz123/FlexiCT-3D-VLM", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ricklisz123/FlexiCT-3D-VLM", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_processor_class": null, | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_flexict.FlexiCTImageProcessor", | |
| "AutoProcessor": "processing_flexict.FlexiCTVLMProcessor" | |
| }, | |
| "clip_range": [ | |
| -1000.0, | |
| 1000.0 | |
| ], | |
| "do_orient_lps": true, | |
| "do_resample": true, | |
| "eps": 1e-06, | |
| "image_processor_type": "FlexiCTImageProcessor", | |
| "image_size": [ | |
| 160, | |
| 160, | |
| 160 | |
| ], | |
| "max_length": 8192, | |
| "model_variant": "vlm", | |
| "preset": "default", | |
| "processor_class": "FlexiCTVLMProcessor", | |
| "target_spacing": [ | |
| 2.0, | |
| 2.0, | |
| 2.0 | |
| ], | |
| "text_model_id": "Qwen/Qwen3-Embedding-0.6B" | |
| } | |