Instructions to use lucky-verma/driver-license-reader with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lucky-verma/driver-license-reader with Transformers:

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

pipe = pipeline("image-text-to-text", model="lucky-verma/driver-license-reader")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("lucky-verma/driver-license-reader")
model = AutoModelForMultimodalLM.from_pretrained("lucky-verma/driver-license-reader")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lucky-verma/driver-license-reader with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lucky-verma/driver-license-reader

SGLang

How to use lucky-verma/driver-license-reader 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 "lucky-verma/driver-license-reader" \
    --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": "lucky-verma/driver-license-reader",
		"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 "lucky-verma/driver-license-reader" \
        --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": "lucky-verma/driver-license-reader",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lucky-verma/driver-license-reader with Docker Model Runner:
```
docker model run hf.co/lucky-verma/driver-license-reader
```

driver-license-reader / preprocessor_config.json

Commit History

Training done

e4b42a8

Lucky Verma commited on Feb 7, 2023

Training done

0bafde2

Lucky Verma commited on Feb 6, 2023

Training done

ca74a60

Lucky Verma commited on Jan 4, 2023

Commit History

Training done e4b42a8

Training done 0bafde2

Training done ca74a60

Training done

e4b42a8

Training done

0bafde2

Training done

ca74a60