Instructions to use mrseongminkim/ReSyn-byt5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrseongminkim/ReSyn-byt5-small with Transformers:

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

pipe = pipeline("text-generation", model="mrseongminkim/ReSyn-byt5-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mrseongminkim/ReSyn-byt5-small")
model = AutoModelForMultimodalLM.from_pretrained("mrseongminkim/ReSyn-byt5-small")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrseongminkim/ReSyn-byt5-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrseongminkim/ReSyn-byt5-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrseongminkim/ReSyn-byt5-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrseongminkim/ReSyn-byt5-small

SGLang

How to use mrseongminkim/ReSyn-byt5-small 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 "mrseongminkim/ReSyn-byt5-small" \
    --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": "mrseongminkim/ReSyn-byt5-small",
		"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 "mrseongminkim/ReSyn-byt5-small" \
        --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": "mrseongminkim/ReSyn-byt5-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrseongminkim/ReSyn-byt5-small with Docker Model Runner:
```
docker model run hf.co/mrseongminkim/ReSyn-byt5-small
```

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

This repository contains the pre-trained Prax model (a ByT5-small baseline) presented in the paper ReSyn: A Generalized Recursive Regular Expression Synthesis Framework.

ReSyn is a synthesizer-agnostic divide-and-conquer framework that decomposes complex regular expression synthesis problems into manageable sub-problems by adaptively predicting whether to split examples sequentially (Concatenation) or group them by structural similarity (Union).

Citation

If you find this work useful, please cite:

@inproceedings{kim2026resyn,
  title={ReSyn: A Generalized Recursive Regular Expression Synthesis Framework},
  author={Kim, Seongmin and Cheon, Hyunjoon and Kim, Su-Hyeon and Han, Yo-Sub and Ko, Sang-Ki},
  booktitle={Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-26)},
  year={2026}
}

Downloads last month: 12

Safetensors

Model size

0.3B params

Tensor type

F32

Paper for mrseongminkim/ReSyn-byt5-small

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

Paper • 2603.24624 • Published 7 days ago

mrseongminkim
/

ReSyn-byt5-small

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework

Links

Citation

Paper for mrseongminkim/ReSyn-byt5-small

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework