Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
nemotron-colembed-vl-4b-v2
like
6
Follow
NVIDIA
49.6k
Visual Document Retrieval
Transformers
Safetensors
ColPali
multilingual
qwen3_vl_nemotron_embed
feature-extraction
text
image
vidore
multimodal-embedding
multilingual-embedding
Text-to-Visual Document (T→VD) retrieval
custom_code
arxiv:
2511.21631
arxiv:
2507.05513
arxiv:
2407.15831
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
nemotron-colembed-vl-4b-v2
9.67 GB
4 contributors
History:
21 commits
BoLiu
Update README.md
da25f84
verified
about 5 hours ago
.gitattributes
1.57 kB
Upload folder using huggingface_hub
20 days ago
CONTRIBUTING.md
2.16 kB
Upload CONTRIBUTING.md
15 days ago
LICENSE
30.9 kB
Update LICENSE
14 days ago
README.md
16.6 kB
Update README.md
about 5 hours ago
THIRD_PARTY_NOTICES.md
36.6 kB
Update THIRD_PARTY_NOTICES.md
19 days ago
chat_template.jinja
5.29 kB
Upload folder using huggingface_hub
20 days ago
config.json
1.88 kB
Upload folder using huggingface_hub
20 days ago
generation_config.json
145 Bytes
Upload folder using huggingface_hub
20 days ago
model-00001-of-00002.safetensors
4.99 GB
xet
Upload folder using huggingface_hub
20 days ago
model-00002-of-00002.safetensors
4.66 GB
xet
Upload folder using huggingface_hub
20 days ago
model.safetensors.index.json
64.8 kB
Upload folder using huggingface_hub
20 days ago
modeling_qwen3_vl_nemotron_embed.py
18.2 kB
Update padding implementation reduced memory footprint
13 days ago
mteb2_eval.py
3.37 kB
Add -vl suffix
19 days ago
processing_qwen3_vl_nemotron_embed.py
9.23 kB
Update processor to handle missing min_pixels/max_pixels in transformers 5.0.0 (#1)
3 days ago
processor_config.json
2.1 kB
Update processor to handle missing min_pixels/max_pixels in transformers 5.0.0 (#1)
3 days ago
tokenizer.json
11.4 MB
xet
Upload folder using huggingface_hub
20 days ago
tokenizer_config.json
768 Bytes
Upload folder using huggingface_hub
20 days ago
