cyberagent/crello
Viewer • Updated • 23.3k • 5.82k • 50
How to use cyberagent/markupdm with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="cyberagent/markupdm", trust_remote_code=True) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cyberagent/markupdm", trust_remote_code=True, dtype="auto")How to use cyberagent/markupdm with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyberagent/markupdm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "cyberagent/markupdm",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/cyberagent/markupdm
How to use cyberagent/markupdm with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "cyberagent/markupdm" \
--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": "cyberagent/markupdm",
"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 "cyberagent/markupdm" \
--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": "cyberagent/markupdm",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use cyberagent/markupdm with Docker Model Runner:
docker model run hf.co/cyberagent/markupdm
This repository provides the pre-trained MarkupDM model for graphic design completion. The model can automatically complete partially designed graphics by generating appropriate text/visual content, positioning, and styling, as demonstrated in our paper Multimodal Markup Document Models for Graphic Design Completion.
For detailed usage instructions, please refer to the MarkupDM GitHub repository.
This repository is released under the Apache-2.0 license.
@inproceedings{Kikuchi2025,
title = {Multimodal Markup Document Models for Graphic Design Completion},
author = {Kotaro Kikuchi and Ukyo Honda and Naoto Inoue and Mayu Otani and Edgar Simo-Serra and Kota Yamaguchi},
booktitle = {ACM International Conference on Multimedia},
year = {2025},
doi = {10.1145/3746027.3755420}
}
Base model
bigcode/starcoderbase-7b