Instructions to use Yuan-Che/OpenECADv2-CLIP-0.55B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yuan-Che/OpenECADv2-CLIP-0.55B with Transformers:

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

pipe = pipeline("text-generation", model="Yuan-Che/OpenECADv2-CLIP-0.55B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Yuan-Che/OpenECADv2-CLIP-0.55B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Yuan-Che/OpenECADv2-CLIP-0.55B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yuan-Che/OpenECADv2-CLIP-0.55B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuan-Che/OpenECADv2-CLIP-0.55B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yuan-Che/OpenECADv2-CLIP-0.55B

SGLang

How to use Yuan-Che/OpenECADv2-CLIP-0.55B 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 "Yuan-Che/OpenECADv2-CLIP-0.55B" \
    --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": "Yuan-Che/OpenECADv2-CLIP-0.55B",
		"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 "Yuan-Che/OpenECADv2-CLIP-0.55B" \
        --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": "Yuan-Che/OpenECADv2-CLIP-0.55B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yuan-Che/OpenECADv2-CLIP-0.55B with Docker Model Runner:
```
docker model run hf.co/Yuan-Che/OpenECADv2-CLIP-0.55B
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

OpenECAD Models

This repo releases models introducing in OpenECAD (2406.09913v3).

The outputs of the OpenECAD models can be converted into STEP files by this tool: YuanZhe-99/OpenECADv2toSTEP.

You can use the model execution method mentioned in TinyLLaVA directly. (TinyLLaVA: Launch Demo Locally)

Downloads last month: 8

Safetensors

Model size

0.5B params

Tensor type

F16

Collection including Yuan-Che/OpenECADv2-CLIP-0.55B

OpenECADv2

Collection

Models and Datasets introducing in OpenECAD (2406.09913[v3]). • 6 items • Updated Aug 27, 2025

Paper for Yuan-Che/OpenECADv2-CLIP-0.55B

OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design

Paper • 2406.09913 • Published Jun 14, 2024