| base_model: vidore/colpaligemma-3b-mix-448-base | |
| library_name: peft | |
| # Model Card for Model ID | |
| <!-- Provide a quick summary of what the model is/does. --> | |
| ## Model Details | |
| ### Model Description | |
| <!-- Provide a longer summary of what this model is. --> | |
| - **Model type:** PaliGemma | |
| - **Finetuned from model [optional]:** vidore/colpali-v1.2 | |
| ## Uses | |
| This model is finetuned from `vidore/colpali-v1.2` using the PEFT library. To use this model, you only need to change the path ColPali is loaded from. | |
| ```python | |
| device = get_torch_device("auto") | |
| print(f"Device used: {device}") | |
| # Model name | |
| model_name = "path/to/fine_tuned_model" | |
| # Load model | |
| model = ColPali.from_pretrained( | |
| model_name, | |
| torch_dtype=torch.bfloat16, | |
| device_map=device, | |
| ).eval() | |
| # Load processor | |
| processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name)) | |
| ``` | |
| - PEFT 0.11.1 |