Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Crossberry
/
Deep
like
0
Image-Text-to-Text
Transformers
Safetensors
multilingual
deepseek_vl_v2
feature-extraction
deepseek
vision-language
ocr
custom_code
arxiv:
2510.18234
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Deep
10.5 MB
1 contributor
History:
6 commits
Crossberry
Upload 5 files
8409586
verified
13 days ago
assets
Upload 5 files
13 days ago
.gitattributes
Safe
1.78 kB
Upload 14 files
13 days ago
LICENSE
Safe
1.08 kB
Upload 14 files
13 days ago
README.md
Safe
6.31 kB
Upload 14 files
13 days ago
config.json
Safe
2.67 kB
Upload 14 files
13 days ago
configuration_deepseek_v2.py
Safe
10.6 kB
Upload 14 files
13 days ago
conversation.py
Safe
9.25 kB
Upload 14 files
13 days ago
deepencoder.py
Safe
38 kB
Upload 14 files
13 days ago
model-00001-of-000001.safetensors
135 Bytes
xet
Upload 14 files
13 days ago
model.safetensors.index.json
Safe
247 kB
Upload 14 files
13 days ago
modeling_deepseekocr.py
Safe
40.1 kB
Upload 14 files
13 days ago
processor_config.json
Safe
460 Bytes
Upload 14 files
13 days ago
special_tokens_map.json
801 Bytes
Upload 14 files
13 days ago
tokenizer.json
Safe
9.98 MB
Upload 14 files
13 days ago
tokenizer_config.json
Safe
166 kB
Upload 14 files
13 days ago