Instructions to use CCCCCC/VPO-5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CCCCCC/VPO-5B with Transformers:

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

pipe = pipeline("text-generation", model="CCCCCC/VPO-5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CCCCCC/VPO-5B")
model = AutoModelForCausalLM.from_pretrained("CCCCCC/VPO-5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CCCCCC/VPO-5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CCCCCC/VPO-5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CCCCCC/VPO-5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CCCCCC/VPO-5B

SGLang

How to use CCCCCC/VPO-5B 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 "CCCCCC/VPO-5B" \
    --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": "CCCCCC/VPO-5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "CCCCCC/VPO-5B" \
        --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": "CCCCCC/VPO-5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CCCCCC/VPO-5B with Docker Model Runner:
```
docker model run hf.co/CCCCCC/VPO-5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

Repository: https://github.com/thu-coai/VPO
Paper: VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
Data: https://huggingface.co/datasets/CCCCCC/VPO

VPO

VPO is a principled prompt optimization framework grounded in the principles of harmlessness, accuracy, and helpfulness. VPO employs a two-stage process that first constructs a supervised fine-tuning dataset guided by safety and alignment, and then conducts preference learning with both text-level and video-level feedback. As a result, VPO preserves user intent while enhancing video quality and safety.

Model Details

Video Generation Model

This model is trained to optimize user prompt for CogVideoX-5B. VPO-2B is for CogVideoX-2B.

Data

Our dataset can be found here.

Language

English

Intended Use

Prompt Template

We adopt a prompt template as

In this task, your goal is to expand the user's short query into a detailed and well-structured English prompt for generating short videos.

Please ensure that the generated video prompt adheres to the following principles:

1. **Harmless**: The prompt must be safe, respectful, and free from any harmful, offensive, or unethical content.  
2. **Aligned**: The prompt should fully preserve the user's intent, incorporating all relevant details from the original query while ensuring clarity and coherence.  
3. **Helpful for High-Quality Video Generation**: The prompt should be descriptive and vivid to facilitate high-quality video creation. Keep the scene feasible and well-suited for a brief duration, avoiding unnecessary complexity or unrealistic elements not mentioned in the query.

User Query:{user prompt}

Video Prompt:

Inference code

Here is an example code for inference:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = ''

prompt_template = """In this task, your goal is to expand the user's short query into a detailed and well-structured English prompt for generating short videos.

Please ensure that the generated video prompt adheres to the following principles:

1. **Harmless**: The prompt must be safe, respectful, and free from any harmful, offensive, or unethical content.  
2. **Aligned**: The prompt should fully preserve the user's intent, incorporating all relevant details from the original query while ensuring clarity and coherence.  
3. **Helpful for High-Quality Video Generation**: The prompt should be descriptive and vivid to facilitate high-quality video creation. Keep the scene feasible and well-suited for a brief duration, avoiding unnecessary complexity or unrealistic elements not mentioned in the query.

User Query:{}

Video Prompt:"""

device = 'cuda:0'
model = AutoModelForCausalLM.from_pretrained(model_path).half().eval().to(device)
# for 8bit
# model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device, load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = "a cute dog on the grass"
messgae = [{'role': 'user', 'content': prompt_template.format(text)}]

model_inputs = tokenizer.apply_chat_template(messgae, add_generation_prompt=True, tokenize=True, return_tensors="pt").to(device)
output = model.generate(model_inputs, max_new_tokens=1024, do_sample=True, top_p=1.0, temperature=0.7, num_beams=1)
resp = tokenizer.decode(output[0]).split('<|start_header_id|>assistant<|end_header_id|>')[1].split('<|eot_id|>')[0].strip()

print(resp)

See our Github Repo for more detailed usage (e.g. Inference with Vllm).

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for CCCCCC/VPO-5B

Quantizations

1 model

Paper for CCCCCC/VPO-5B

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

Paper • 2503.20491 • Published Mar 26, 2025 • 1