Downloads · 30 days
15
36% of all-time downloads
OCR-int4-merged
SamMikaelson/OCR-int4-merged
OCR-int4-merged is a machine learning model from SamMikaelson. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
This is a merged version of the DeepSeek-OCR model that was quantized to INT4 and then dequantized back to full precision.
All-time downloads
42
Public
Parameters
1.4B
5.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.5 GB · 100%
At a glance
- License
- other
- Model type
- DeepseekOCR
- Access
- Public
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025
- SHA
- 27249ecb
Base models
Model card
From the Hugging Face model README
DeepSeek-OCR INT4 Merged Model
This is a merged version of the DeepSeek-OCR model that was quantized to INT4 and then dequantized back to full precision.
Model Details
- Base Model: deepseek-ai/DeepSeek-OCR
- Quantization: INT4 (during storage)
- Final Format: Full precision (FP32/FP16)
Usage
from transformers import AutoModelForCausalLM, AutoProcessor
from PIL import Image
# Load model and processor
model = AutoModelForCausalLM.from_pretrained(
"YOUR_USERNAME/OCR-int4-merged",
trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(
"YOUR_USERNAME/OCR-int4-merged",
trust_remote_code=True
)
# Process image
image = Image.open("document.jpg")
inputs = processor(images=image, return_tensors="pt")
# Generate OCR output
outputs = model.generate(**inputs, max_new_tokens=512)
text = processor.decode(outputs[0], skip_special_tokens=True)
print(text)
Notes
This model was created by:
- Quantizing the original DeepSeek-OCR to INT4
- Dequantizing back to full precision
- Merging into a standard model format
The process allows for efficient storage and distribution while maintaining full model capabilities.
- Type
- DeepseekOCR
- License
- other
- Languages
- en, zh
- Created
- Dec 13, 2025
- Updated
- Dec 13, 2025