Instructions to use laicsiifes/phi3-vision-flickr30k_pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use laicsiifes/phi3-vision-flickr30k_pt with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("laicsiifes/phi3-vision-flickr30k_pt", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "microsoft/Phi-3-vision-128k-instruct--image_processing_phi3_v.Phi3VImageProcessor", | |
| "AutoProcessor": "microsoft/Phi-3-vision-128k-instruct--processing_phi3_v.Phi3VProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Phi3VImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "num_crops": 16, | |
| "num_img_tokens": 144, | |
| "processor_class": "Phi3VProcessor" | |
| } | |