Instructions to use Azu/trocr-handwritten-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azu/trocr-handwritten-math with Transformers:

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

pipe = pipeline("image-text-to-text", model="Azu/trocr-handwritten-math")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Azu/trocr-handwritten-math")
model = AutoModelForMultimodalLM.from_pretrained("Azu/trocr-handwritten-math", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azu/trocr-handwritten-math with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Azu/trocr-handwritten-math

SGLang

How to use Azu/trocr-handwritten-math 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 "Azu/trocr-handwritten-math" \
    --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": "Azu/trocr-handwritten-math",
		"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 "Azu/trocr-handwritten-math" \
        --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": "Azu/trocr-handwritten-math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Azu/trocr-handwritten-math with Docker Model Runner:
```
docker model run hf.co/Azu/trocr-handwritten-math
```

trocr-handwritten-math

Commit History

Mar 2, 2025

13:50
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
5de2eb1

Mar 11, 2022

13:00
Create README.md

Azu

fc8dc98
12:56
Add model

Azu

7b75bf0
12:51
initial commit

Azu

bc56e9b

Commit History

Mar 2, 2025

Adding `safetensors` variant of this model⁠

Mar 11, 2022

Create README.md

Add model

initial commit