UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
Paper • 2404.15254 • Published • 1
How to use wanderkid/unimernet with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="wanderkid/unimernet") # Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText
tokenizer = AutoTokenizer.from_pretrained("wanderkid/unimernet")
model = AutoModelForImageTextToText.from_pretrained("wanderkid/unimernet")How to use wanderkid/unimernet with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wanderkid/unimernet"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "wanderkid/unimernet",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/wanderkid/unimernet
How to use wanderkid/unimernet with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "wanderkid/unimernet" \
--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": "wanderkid/unimernet",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "wanderkid/unimernet" \
--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": "wanderkid/unimernet",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use wanderkid/unimernet with Docker Model Runner:
docker model run hf.co/wanderkid/unimernet
UniMERNet: A Universal Network for Mathematical Expression Recognition in Real-World Scenarios.
Visit our GitHub repository at unimernet for more information.
Citations
@misc{wang2024unimernet,
title={UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition},
author={Bin Wang and Zhuangcheng Gu and Chao Xu and Bo Zhang and Botian Shi and Conghui He},
year={2024},
eprint={2404.15254},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@misc{conghui2022opendatalab,
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Wang, Bin and Xu, Chao and Lin, Dahua},
title={OpenDataLab: Empowering General Artificial Intelligence with Open Datasets},
howpublished = {\url{https://opendatalab.com}},
year={2022}
}