Instructions to use Coobiw/ChartMoE-Aligned-Connector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Coobiw/ChartMoE-Aligned-Connector with Transformers:

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

pipe = pipeline("image-text-to-text", model="Coobiw/ChartMoE-Aligned-Connector")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Coobiw/ChartMoE-Aligned-Connector", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Coobiw/ChartMoE-Aligned-Connector with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Coobiw/ChartMoE-Aligned-Connector

SGLang

How to use Coobiw/ChartMoE-Aligned-Connector 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 "Coobiw/ChartMoE-Aligned-Connector" \
    --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": "Coobiw/ChartMoE-Aligned-Connector",
		"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 "Coobiw/ChartMoE-Aligned-Connector" \
        --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": "Coobiw/ChartMoE-Aligned-Connector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Coobiw/ChartMoE-Aligned-Connector with Docker Model Runner:
```
docker model run hf.co/Coobiw/ChartMoE-Aligned-Connector
```

ChartMoE

ICLR2025 Oral

ChartMoE is a multimodal large language model with Mixture-of-Expert connector, based on InternLM-XComposer2 for advanced chart 1)understanding, 2)replot, 3)editing, 4)highlighting and 5)transformation.

This is a reproduction of diversely-aligner moe-connector, please feel free to use it for continue sft training!

Open Source License

The data is licensed under Apache-2.0.

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

Collection including Coobiw/ChartMoE-Aligned-Connector

ChartMoE(ICLR2025 Oral)

Collection

[ICLR2025 Oral] ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding github: https://github.com/IDEA-FinAI/ChartMoE • 6 items • Updated Mar 6, 2025

Paper for Coobiw/ChartMoE-Aligned-Connector

ChartMoE: Mixture of Expert Connector for Advanced Chart Understanding

Paper • 2409.03277 • Published Sep 5, 2024 • 1