SamMikaelson
/

deepseek-ocr-mbq-w4bit

Feature Extraction

vision-language

Model card Files Files and versions

deepseek-ocr-mbq-w4bit

3.53 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

SamMikaelson's picture

Add modeling_deepseekv2.py

255ada8 verified 2 months ago

.gitattributes

1.52 kB

initial commit 2 months ago
README.md

6.08 kB

Add README.md 2 months ago
config.json

3.32 kB

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
configuration_deepseek_v2.py

10.6 kB

Add configuration_deepseek_v2.py 2 months ago
load_mbq_model.py

1.06 kB

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
model.safetensors

3.51 GB
xet

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
modeling_deepseekocr.py

40.1 kB

Add modeling_deepseekocr.py 2 months ago
modeling_deepseekv2.py

82.2 kB

Add modeling_deepseekv2.py 2 months ago
quantization_metadata.json

279 kB

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
quantization_report.json

918 Bytes

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
requirements.txt

86 Bytes

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
special_tokens_map.json

549 Bytes

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
tokenizer.json

9.98 MB

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago
tokenizer_config.json

166 kB

Upload MBQ quantized model (W4A8) - 65.05% size reduction 2 months ago