Instructions to use GD-ML/UniVG-R1-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GD-ML/UniVG-R1-stage1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="GD-ML/UniVG-R1-stage1")
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("GD-ML/UniVG-R1-stage1")
model = AutoModelForImageTextToText.from_pretrained("GD-ML/UniVG-R1-stage1")
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 GD-ML/UniVG-R1-stage1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GD-ML/UniVG-R1-stage1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GD-ML/UniVG-R1-stage1",
		"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/GD-ML/UniVG-R1-stage1

SGLang

How to use GD-ML/UniVG-R1-stage1 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 "GD-ML/UniVG-R1-stage1" \
    --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": "GD-ML/UniVG-R1-stage1",
		"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 "GD-ML/UniVG-R1-stage1" \
        --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": "GD-ML/UniVG-R1-stage1",
		"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 GD-ML/UniVG-R1-stage1 with Docker Model Runner:
```
docker model run hf.co/GD-ML/UniVG-R1-stage1
```

SuleBai commited on Jun 2, 2025

Commit

865aab1

verified ·

1 Parent(s): 5a49e71

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -43

README.md CHANGED Viewed

@@ -7,52 +7,10 @@ tags:
 - full
 - generated_from_trainer
 model-index:
-- name: Qwen2-VL_7b_full_cot_sft_90k_singlewocot_taskdescriptor_level9
   results: []
 ---
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# Qwen2-VL_7b_full_cot_sft_90k_singlewocot_taskdescriptor_level9
-This model is a fine-tuned version of [Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen2-VL-7B-Instruct) on the cot_sft_90k_singlewocot_taskdescriptor_level9 dataset.
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 3
-- total_train_batch_size: 24
-- total_eval_batch_size: 64
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.015
-- num_epochs: 1.0
-### Training results
 ### Framework versions
 - Transformers 4.49.0

 - full
 - generated_from_trainer
 model-index:
+- name: UniVG-R1-stage1
   results: []
 ---
 ### Framework versions
 - Transformers 4.49.0