Instructions to use OpenIXCLab/CODA-PLANNER-TARS-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenIXCLab/CODA-PLANNER-TARS-32B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenIXCLab/CODA-PLANNER-TARS-32B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OpenIXCLab/CODA-PLANNER-TARS-32B")
model = AutoModelForImageTextToText.from_pretrained("OpenIXCLab/CODA-PLANNER-TARS-32B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenIXCLab/CODA-PLANNER-TARS-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenIXCLab/CODA-PLANNER-TARS-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenIXCLab/CODA-PLANNER-TARS-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OpenIXCLab/CODA-PLANNER-TARS-32B

SGLang

How to use OpenIXCLab/CODA-PLANNER-TARS-32B 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 "OpenIXCLab/CODA-PLANNER-TARS-32B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenIXCLab/CODA-PLANNER-TARS-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "OpenIXCLab/CODA-PLANNER-TARS-32B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenIXCLab/CODA-PLANNER-TARS-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OpenIXCLab/CODA-PLANNER-TARS-32B with Docker Model Runner:
```
docker model run hf.co/OpenIXCLab/CODA-PLANNER-TARS-32B
```

Improve model card: add abstract, usage, features, and fix license metadata

by nielsr HF Staff - opened Aug 31, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+115

-8

nielsr

Aug 31, 2025

This PR significantly enhances the model card by:

Correcting a typo in the metadata (licence to license) to ensure proper classification and display on the Hub.
Adding the paper's abstract to provide a comprehensive overview of the model's capabilities and research.
Including a detailed "Features" section derived from the abstract to highlight key aspects of CODA.
Providing a "Usage" section with installation and inference shell commands directly from the GitHub repository, making it easier for users to try out the model.
Adding the full BibTeX citation for easier referencing.
Expanding the license information in the content for clarity.

These changes will make the model card more informative and user-friendly.

Improve model card: add abstract, usage, features, and fix license metadata66f8eb42

Zery changed pull request status to merged Aug 31, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment