Visual Document Retrieval
Transformers
Safetensors
ColPali
multilingual
colqwen3
feature-extraction
text
image
video
multimodal-embedding
vidore
multilingual-embedding
custom_code
Instructions to use TomoroAI/tomoro-colqwen3-embed-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TomoroAI/tomoro-colqwen3-embed-4b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TomoroAI/tomoro-colqwen3-embed-4b", trust_remote_code=True, dtype="auto") - ColPali
How to use TomoroAI/tomoro-colqwen3-embed-4b with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_colqwen3.ColQwen3Processor" | |
| }, | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "disable_grouping": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": null, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessorFast", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_pixels": 1310720, | |
| "merge_size": 2, | |
| "min_pixels": null, | |
| "pad_size": null, | |
| "patch_size": 16, | |
| "processor_class": "ColQwen3Processor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 1310720, | |
| "shortest_edge": 65536 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |