Image-to-Text
Transformers
Safetensors
florence2
image-text-to-text
florence-2
deepfake-detection
computer-vision
multimodal
lora
custom_code
Instructions to use zelus82/verity-1A with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zelus82/verity-1A with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="zelus82/verity-1A", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("zelus82/verity-1A", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("zelus82/verity-1A", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from zelus82/verity-1A: direct link, hf CLI and curl.
- Browser
- Download file 603 Bytes
-
https://huggingface.co/zelus82/verity-1A/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://zelus82/verity-1A/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/zelus82/verity-1A/resolve/main/preprocessor_config.json
603 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_florence2.Florence2Processor" | |
| }, | |
| "crop_size": { | |
| "height": 768, | |
| "width": 768 | |
| }, | |
| "do_center_crop": false, | |
| "do_convert_rgb": null, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "CLIPImageProcessor", | |
| "image_seq_length": 577, | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "processor_class": "Florence2Processor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 768, | |
| "width": 768 | |
| } | |
| } | |