Instructions to use SamMikaelson/deepseek-ocr-int8-uniform with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SamMikaelson/deepseek-ocr-int8-uniform with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="SamMikaelson/deepseek-ocr-int8-uniform")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SamMikaelson/deepseek-ocr-int8-uniform", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SamMikaelson/deepseek-ocr-int8-uniform with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SamMikaelson/deepseek-ocr-int8-uniform"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SamMikaelson/deepseek-ocr-int8-uniform",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SamMikaelson/deepseek-ocr-int8-uniform

SGLang

How to use SamMikaelson/deepseek-ocr-int8-uniform with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SamMikaelson/deepseek-ocr-int8-uniform" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SamMikaelson/deepseek-ocr-int8-uniform",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SamMikaelson/deepseek-ocr-int8-uniform" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SamMikaelson/deepseek-ocr-int8-uniform",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SamMikaelson/deepseek-ocr-int8-uniform with Docker Model Runner:
```
docker model run hf.co/SamMikaelson/deepseek-ocr-int8-uniform
```

DeepSeek-OCR INT8 Quantized (Safetensors)

Uniformly quantized version of DeepSeek-OCR using safetensors format + JSON metadata.

📊 Model Stats

Original Size: 6363.12 MB
Compressed Size: 3351.56 MB
Saved Size: 3352.37 MB
Compression Ratio: 1.90x
Format: Safetensors + JSON metadata

🚀 Quick Start

from model_loader import load_quantized_model

model = load_quantized_model(
    "SamMikaelson/deepseek-ocr-int8-uniform",
    device="cuda"
)

# Model is ready to use!
# Memory footprint: ~3352 MB

🔧 Manual Loading

import torch
from safetensors.torch import load_file
import json

# Load weights
state_dict = load_file("model.safetensors")

# Load metadata
with open("quantization_config.json") as f:
    metadata = json.load(f)

# Reconstruct model (see model_loader.py for details)

📦 File Structure

model.safetensors          # 3352 MB - All weights (compressed)
quantization_config.json   # Layer metadata (bits, shapes)
config.json                # Model config
quantization.py            # QuantizedLinear layer
model_loader.py            # Loading utilities

✨ Why Safetensors?

✅ Secure: No arbitrary code execution (vs pickle)
✅ Fast: Zero-copy loading
✅ Standard: HuggingFace official format
✅ Portable: Works across frameworks

📊 Quantization Details

Method: Uniform INT8
Vision layers: 96 @ 8-bit
Language layers: 2197 @ 8-bit
Dequantization: On-the-fly during forward pass

🔍 Inspect Metadata

import json

with open("quantization_config.json") as f:
    config = json.load(f)

print(f"Quantized layers: {len(config['quantized_layers'])}")
print(f"Compression: {config['stats']['compression_ratio']}x")

📝 License

MIT (inherited from DeepSeek-OCR)

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

I64

F32

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support