Instructions to use ChartFoundation/ECD_Finetuned_MLLMs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChartFoundation/ECD_Finetuned_MLLMs with Transformers:

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

pipe = pipeline("image-text-to-text", model="ChartFoundation/ECD_Finetuned_MLLMs")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ChartFoundation/ECD_Finetuned_MLLMs", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ChartFoundation/ECD_Finetuned_MLLMs with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ChartFoundation/ECD_Finetuned_MLLMs

SGLang

How to use ChartFoundation/ECD_Finetuned_MLLMs 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 "ChartFoundation/ECD_Finetuned_MLLMs" \
    --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": "ChartFoundation/ECD_Finetuned_MLLMs",
		"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 "ChartFoundation/ECD_Finetuned_MLLMs" \
        --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": "ChartFoundation/ECD_Finetuned_MLLMs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChartFoundation/ECD_Finetuned_MLLMs with Docker Model Runner:
```
docker model run hf.co/ChartFoundation/ECD_Finetuned_MLLMs
```

The following models are obtained via supervised fine-tuning (SFT) using the ECD-10k-Images dataset (URL) proposed in our ICCV 2025 paper, "Effective Training Data Synthesis for Improving MLLM Chart Understanding" (Code).

ECD Dataset Overview:

Comparing 4 MLLMs on six test sets: (CharXiv, ChartQA, ReachQA, ChartBench, ChartX, ECDBench)

Citation:

If it is helpful to your research, please cite our paper as follows:

@inproceedings{yang2025effective,
     title={Effective Training Data Synthesis for Improving MLLM Chart Understanding},
     author={Yang, Yuwei and Zhang, Zeyu and Hou, Yunzhong and Li, Zhuowan and Liu, Gaowen and Payani, Ali and Ting, Yuan-Sen and Zheng, Liang},
     booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     year={2025}
 }

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ChartFoundation/ECD_Finetuned_MLLMs

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1073)

this model

Paper for ChartFoundation/ECD_Finetuned_MLLMs

Effective Training Data Synthesis for Improving MLLM Chart Understanding

Paper • 2508.06492 • Published Aug 8, 2025 • 3