Instructions to use culturalheritagenus/Jawi-OCR-Qwen-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use culturalheritagenus/Jawi-OCR-Qwen-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="culturalheritagenus/Jawi-OCR-Qwen-v1")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("culturalheritagenus/Jawi-OCR-Qwen-v1")
model = AutoModelForMultimodalLM.from_pretrained("culturalheritagenus/Jawi-OCR-Qwen-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use culturalheritagenus/Jawi-OCR-Qwen-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/culturalheritagenus/Jawi-OCR-Qwen-v1

SGLang

How to use culturalheritagenus/Jawi-OCR-Qwen-v1 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 "culturalheritagenus/Jawi-OCR-Qwen-v1" \
    --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": "culturalheritagenus/Jawi-OCR-Qwen-v1",
		"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 "culturalheritagenus/Jawi-OCR-Qwen-v1" \
        --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": "culturalheritagenus/Jawi-OCR-Qwen-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use culturalheritagenus/Jawi-OCR-Qwen-v1 with Docker Model Runner:
```
docker model run hf.co/culturalheritagenus/Jawi-OCR-Qwen-v1
```

totallynotalvin commited on Jul 31, 2025

Commit

49019ec

1 Parent(s): 3387248

fix: fix reqs with extra url

Browse files

Files changed (1) hide show

requirements.txt +6 -7

requirements.txt CHANGED Viewed

@@ -1,15 +1,14 @@
-# For CUDA 11.8 (recommended for Qwen2VL)
---index-url https://download.pytorch.org/whl/cu118
-torch==2.1.0+cu118
-torchvision==0.16.0+cu118
 # Core dependencies for Qwen2VL
-transformers>=4.37.0
-git+https://github.com/QwenLM/Qwen2-VL.git#subdirectory=qwen-vl-utils
 accelerate
 safetensors
 Pillow>=8.0.0
 # Additional dependencies
 numpy
 requests

+--extra-index-url https://download.pytorch.org/whl/cu118
 # Core dependencies for Qwen2VL
+transformers
+qwen-vl-utils
 accelerate
 safetensors
 Pillow>=8.0.0
 # Additional dependencies
 numpy
 requests
+# PyTorch with CUDA 11.8
+torch==2.1.0+cu118
+torchvision==0.16.0+cu118