Instructions to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with Transformers:

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

pipe = pipeline("image-text-to-text", model="LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
model = AutoModelForMultimodalLM.from_pretrained("LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
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 Settings

vLLM

How to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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/LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start

SGLang

How to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start 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 "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start" \
    --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": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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 "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start" \
        --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": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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 LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with Docker Model Runner:
```
docker model run hf.co/LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start
```

Improve model card: Add pipeline tag, paper link, abstract, code, and usage

by nielsr HF Staff - opened Aug 31, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+108

-8

nielsr

Aug 31, 2025

This PR significantly improves the model card for Qwen2.5-VL-3B-Instruct by:

Adding essential metadata:
- Adding pipeline_tag: image-text-to-text, ensuring the model is discoverable under the correct category on the Hub (https://huggingface.co/models?pipeline_tag=image-text-to-text).
- Adding vision-language-model to the existing tags.
Enriching content:
- Updating the main title to include the paper name for clarity.
- Adding the paper title and a direct link to its Hugging Face page: Self-Rewarding Vision-Language Model via Reasoning Decomposition.
- Including the full paper abstract for a detailed overview.
- Adding a clear link to the GitHub repository (https://github.com/zli12321/Vision-SR1).
- Populating the "Model description", "Intended uses & limitations", and "Training and evaluation data" sections with information extracted from the paper and the GitHub README.
- Adding a "Sample Usage" section with direct code snippets (bash commands) for setup, training, merging, and evaluation response generation, as found in the original GitHub README.
- Adding the training reward progression image.
- Adding the citation for the EasyR1 source code as specified in the GitHub README.

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

Improve model card: Add pipeline tag, paper link, abstract, code, and usage2e7f0a63

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment