Feature Extraction
Transformers
Safetensors
lumen
pathology
vision-language
histopathology
lora
zero-shot
custom_code
Instructions to use digitalpathologybern/Lumen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitalpathologybern/Lumen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="digitalpathologybern/Lumen", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("digitalpathologybern/Lumen", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from digitalpathologybern/Lumen: direct link, hf CLI and curl.
- Browser
- Download file 448 Bytes
-
https://huggingface.co/digitalpathologybern/Lumen/resolve/main/config.json
- Command line
-
hf download hf://digitalpathologybern/Lumen/config.json
-
curl -L -o config.json https://huggingface.co/digitalpathologybern/Lumen/resolve/main/config.json
448 Bytes
| { | |
| "model_type": "lumen", | |
| "architectures": [ | |
| "LumenModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_lumen.LumenConfig", | |
| "AutoModel": "modeling_lumen.LumenModel" | |
| }, | |
| "vision_repo": "paige-ai/Virchow2", | |
| "text_repo": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext", | |
| "proj_dim": 512, | |
| "vision_dim": 2560, | |
| "text_dim": 768, | |
| "lora_r": 4, | |
| "lora_alpha": 8, | |
| "lora_dropout": 0.1, | |
| "torch_dtype": "float32" | |
| } | |