Instructions to use convergence-ai/proxy-lite-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use convergence-ai/proxy-lite-3b with Transformers:

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

pipe = pipeline("image-text-to-text", model="convergence-ai/proxy-lite-3b")
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("convergence-ai/proxy-lite-3b")
model = AutoModelForImageTextToText.from_pretrained("convergence-ai/proxy-lite-3b")
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 convergence-ai/proxy-lite-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "convergence-ai/proxy-lite-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "convergence-ai/proxy-lite-3b",
		"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/convergence-ai/proxy-lite-3b

SGLang

How to use convergence-ai/proxy-lite-3b 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 "convergence-ai/proxy-lite-3b" \
    --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": "convergence-ai/proxy-lite-3b",
		"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 "convergence-ai/proxy-lite-3b" \
        --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": "convergence-ai/proxy-lite-3b",
		"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 convergence-ai/proxy-lite-3b with Docker Model Runner:
```
docker model run hf.co/convergence-ai/proxy-lite-3b
```

## 🚨License Conflict: CC BY-NC 4.0 May Be Incompatible with Qwen Research License

by xixi126 - opened Jun 20, 2025

Discussion

xixi126

Jun 20, 2025

Hi, I'd like to report a License Conflict in convergence-ai/proxy-lite-3b. I noticed this model was fine-tuned from Qwen/Qwen2.5-VL-3B-Instruct, which is released under the Qwen RESEARCH LICENSE AGREEMENT. From what I can see, HKUSTAudio/Llasa-3B is currently licensed under CC BY-NC 4.0, and that might not be compatible with the original license's requirements.

⚠️ Key violations of Qwen RESEARCH LICENSE AGREEMENT:

Section 3 – Redistribution:
  • You must provide a copy of the Qwen license to all recipients
  • Must include a "NOTICE" file with the attribution text:
    "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."
  • You may add new terms **only if they are compatible** and do not conflict with the original agreement

Section 4.b – Attribution Requirement:
  • Any derivative model must prominently display:
    “Built with Qwen” or “Improved using Qwen”

Section 5.a – Ownership:
  • You’re totally free to make and publish your own modifications — but the original Qwen license still applies to any parts based on it, and it can’t be swapped out or replaced with something like CC BY-NC 4.0.

Changing the license from Qwen RESEARCH LICENSE AGREEMENT to CC BY-NC 4.0 could unintentionally violate the original Qwen terms, especially since:

• Qwen's license requires specific attribution and legal notices
• It does not allow relicensing under incompatible terms
• The legal jurisdiction and disclaimer clauses are not transferable to CC BY-NC 4.0

They might both limit how the model’s used, but Qwen and CC BY-NC work in totally different ways — replacing one with the other could make it really unclear what’s actually allowed.

🔹 Friendly Suggestions😊:

To help keep things aligned with the original license, it might be worth:

✅ Adding the full Qwen Research License to the model card or repository

✅ Including a "NOTICE" file with the required attribution

✅ Clarifying that the model is a derivative of Qwen and follows its license

📝 Optionally noting any additional terms, as long as they don’t conflict with Qwen’s

Really appreciate the awesome work on Proxy-Lite — just raising this to help keep licensing clear for everyone building on top of it. 😊 Let me know if I misunderstood anything — happy to help clarify!

Thanks for your attention!

xixi126 changed discussion title from ## 🚨License Conflict: License Conflict: CC BY-NC 4.0 May Be Incompatible with Qwen Research License to ## 🚨License Conflict: CC BY-NC 4.0 May Be Incompatible with Qwen Research License Jun 20, 2025

xixi126

Jul 10, 2025

Looking forward to your response!

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