Visual Document Retrieval
Transformers
Safetensors
gemma3
image-text-to-text
vision-language
retrieval
multimodal
multilingual
document-retrieval
matryoshka-embeddings
dense-retrieval
22-languages
Eval Results (legacy)
text-generation-inference
Instructions to use Cognitive-Lab/NetraEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cognitive-Lab/NetraEmbed with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Cognitive-Lab/NetraEmbed") model = AutoModelForMultimodalLM.from_pretrained("Cognitive-Lab/NetraEmbed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from Cognitive-Lab/NetraEmbed: direct link, hf CLI and curl.
- Browser
- Download file 662 Bytes
-
https://huggingface.co/Cognitive-Lab/NetraEmbed/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://Cognitive-Lab/NetraEmbed/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/Cognitive-Lab/NetraEmbed/resolve/main/special_tokens_map.json
662 Bytes
| { | |
| "boi_token": "<start_of_image>", | |
| "bos_token": { | |
| "content": "<bos>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eoi_token": "<end_of_image>", | |
| "eos_token": { | |
| "content": "<eos>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "image_token": "<image_soft_token>", | |
| "pad_token": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |