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
2 months ago
assets
Upload 5 files
2 months ago
.gitattributes
1.78 kB
Upload 14 files
2 months ago
LICENSE
1.08 kB
Upload 14 files
2 months ago
README.md
6.31 kB
Upload 14 files
2 months ago
config.json
2.67 kB
Upload 14 files
2 months ago
configuration_deepseek_v2.py
10.6 kB
Upload 14 files
2 months ago
conversation.py
9.25 kB
Upload 14 files
2 months ago
deepencoder.py
38 kB
Upload 14 files
2 months ago
model-00001-of-000001.safetensors
135 Bytes
xet
Upload 14 files
2 months ago
model.safetensors.index.json
247 kB
Upload 14 files
2 months ago
modeling_deepseekocr.py
40.1 kB
Upload 14 files
2 months ago
processor_config.json
460 Bytes
Upload 14 files
2 months ago
special_tokens_map.json
801 Bytes
Upload 14 files
2 months ago
tokenizer.json
9.98 MB
Upload 14 files
2 months ago
tokenizer_config.json
166 kB
Upload 14 files
2 months ago
