Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
SamMikaelson
/
deepseek-ocr-qvlm-4bit
like
0
Image-to-Text
Transformers
Safetensors
deepseek_vl_v2
feature-extraction
vision
ocr
quantized
qvlm
4-bit precision
deepseek
custom_code
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
deepseek-ocr-qvlm-4bit
2.32 GB
1 contributor
History:
69 commits
SamMikaelson
Add config.json with auto_map for standalone loading
520014b
verified
9 days ago
.gitattributes
1.52 kB
initial commit
9 days ago
README.md
4.28 kB
Upload QVLM 4-bit quantized DeepSeek-OCR model (SafeTensors format) - 2.89x compression
9 days ago
config.json
2.87 kB
Add config.json with auto_map for standalone loading
9 days ago
configuration_deepseek_v2.py
10.6 kB
Add configuration_deepseek_v2.py for standalone loading
9 days ago
conversation.py
9.25 kB
Add conversation.py for standalone loading
9 days ago
deepencoder.py
38 kB
Add deepencoder.py for standalone loading
9 days ago
model.safetensors
2.31 GB
xet
Upload QVLM 4-bit quantized DeepSeek-OCR model (SafeTensors format) - 2.89x compression
9 days ago
modeling_deepseekocr.py
40.1 kB
Add modeling_deepseekocr.py for standalone loading
9 days ago
modeling_deepseekv2.py
82.2 kB
Add modeling_deepseekv2.py for standalone loading
9 days ago
processor_config.json
460 Bytes
Add processor_config.json for standalone loading
9 days ago
quantization_config.json
127 Bytes
Upload QVLM 4-bit quantized DeepSeek-OCR model (SafeTensors format) - 2.89x compression
9 days ago
quantization_results.json
547 Bytes
Upload QVLM 4-bit quantized DeepSeek-OCR model (SafeTensors format) - 2.89x compression
9 days ago
special_tokens_map.json
801 Bytes
Add special_tokens_map.json for standalone loading
9 days ago
tokenizer.json
9.98 MB
Add tokenizer.json for standalone loading
9 days ago
tokenizer_config.json
166 kB
Add tokenizer_config.json for standalone loading
9 days ago