Visual Document Retrieval
Transformers
Safetensors
gemma3
image-text-to-text
vision-language
retrieval
colbert
late-interaction
multimodal
multilingual
document-retrieval
22-languages
Eval Results (legacy)
text-generation-inference
Instructions to use Cognitive-Lab/ColNetraEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cognitive-Lab/ColNetraEmbed with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Cognitive-Lab/ColNetraEmbed") model = AutoModelForMultimodalLM.from_pretrained("Cognitive-Lab/ColNetraEmbed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from Cognitive-Lab/ColNetraEmbed: direct link, hf CLI and curl.
- Browser
- Download file 45 Bytes
-
https://huggingface.co/Cognitive-Lab/ColNetraEmbed/resolve/main/processor_config.json
- Command line
-
hf download hf://Cognitive-Lab/ColNetraEmbed/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/Cognitive-Lab/ColNetraEmbed/resolve/main/processor_config.json
45 Bytes
| { | |
| "processor_class": "ColGemmaProcessor3" | |
| } |