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, device_map="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
Update Prerequisites
Browse files
README.md
CHANGED
|
@@ -145,8 +145,12 @@ All below evaluations are using Hit@1 metric.
|
|
| 145 |
The processor exposes `process_texts`, `process_images`, and `score_multi_vector`.
|
| 146 |
|
| 147 |
### Prerequisites
|
|
|
|
|
|
|
|
|
|
| 148 |
```bash
|
| 149 |
-
pip install torch transformers pillow requests
|
|
|
|
| 150 |
````
|
| 151 |
|
| 152 |
### Inference Code
|
|
|
|
| 145 |
The processor exposes `process_texts`, `process_images`, and `score_multi_vector`.
|
| 146 |
|
| 147 |
### Prerequisites
|
| 148 |
+
|
| 149 |
+
Note our model currently requires `flash-attn` to be installed. If you run into slow image encoding issue, please check whether `flash-attn` is installed properly.
|
| 150 |
+
|
| 151 |
```bash
|
| 152 |
+
pip install torch torchvision transformers pillow requests
|
| 153 |
+
pip install flash-attn --no-build-isolation
|
| 154 |
````
|
| 155 |
|
| 156 |
### Inference Code
|