Instructions to use Allen8/TVC-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Allen8/TVC-72B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Allen8/TVC-72B")
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("Allen8/TVC-72B")
model = AutoModelForMultimodalLM.from_pretrained("Allen8/TVC-72B", device_map="auto")
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 Allen8/TVC-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Allen8/TVC-72B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Allen8/TVC-72B",
		"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/Allen8/TVC-72B

SGLang

How to use Allen8/TVC-72B 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 "Allen8/TVC-72B" \
    --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": "Allen8/TVC-72B",
		"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 "Allen8/TVC-72B" \
        --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": "Allen8/TVC-72B",
		"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 Allen8/TVC-72B with Docker Model Runner:
```
docker model run hf.co/Allen8/TVC-72B
```

Model Summary

The TVC models are 72B parameter models based on Qwen2-VL-72B-Instruct model with a context window of 8K tokens.

Repository: https://github.com/sun-hailong/TVC
Languages: English, Chinese
Paper: https://arxiv.org/abs/2503.13360

Model Architecture

Architecture: Qwen2-VL-72B-Instruct
Data: a mixture of 300k long-chain reasoning data
Precision: BFloat16

Hardware & Software

Hardware: 64 * NVIDIA Tesla H20
Orchestration: HuggingFace Trainer
Code: Pytorch

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

Citation

@article{sun2024mitigating,
    title={Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning},
    author={Sun, Hai-Long and Sun, Zhun and Peng, Houwen and Ye, Han-Jia},
    journal={arXiv preprint arXiv:2503.13360},
    year={2025}
}

Downloads last month: 11

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for Allen8/TVC-72B

Base model

Qwen/Qwen2-VL-72B

Finetuned

Qwen/Qwen2-VL-72B-Instruct

Finetuned

(3)

this model

Paper for Allen8/TVC-72B

Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning

Paper • 2503.13360 • Published Mar 17, 2025 • 7