Instructions to use QizhiPei/DiffGen-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QizhiPei/DiffGen-8B with Transformers:

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

pipe = pipeline("text-generation", model="QizhiPei/DiffGen-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QizhiPei/DiffGen-8B")
model = AutoModelForCausalLM.from_pretrained("QizhiPei/DiffGen-8B")
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 QizhiPei/DiffGen-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QizhiPei/DiffGen-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QizhiPei/DiffGen-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QizhiPei/DiffGen-8B

SGLang

How to use QizhiPei/DiffGen-8B 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 "QizhiPei/DiffGen-8B" \
    --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": "QizhiPei/DiffGen-8B",
		"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 "QizhiPei/DiffGen-8B" \
        --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": "QizhiPei/DiffGen-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QizhiPei/DiffGen-8B with Docker Model Runner:
```
docker model run hf.co/QizhiPei/DiffGen-8B
```

Improve model card: Update metadata and enrich content for DiffGen-8B

by nielsr HF Staff - opened Sep 26, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+11

-10

nielsr

Sep 26, 2025

This PR enhances the model card for DiffGen-8B, a key component of the ScaleDiff pipeline, by improving its discoverability and providing more comprehensive information.

Key updates include:

Changing the license from other to apache-2.0, aligning with common practices for research artifacts and inferred from the GitHub repository's license badge.
Adding the pipeline_tag: text-generation to accurately categorize the model's function as a problem generator.
Adding math-reasoning to the tags for better discoverability within the mathematical domain.
Expanding the "Model description", "Intended uses & limitations", and "Training and evaluation data" sections with detailed information extracted from the associated paper abstract and GitHub README.
Removing the auto-generated comment at the top of the model card.

A Sample Usage section is not included, as the provided GitHub README does not contain a direct, ready-to-use inference code snippet for this specific model using the transformers library, adhering to the guideline of not creating code snippets without evidence.

Improve model card: Update metadata and enrich content for DiffGen-8Bcd84ff27

QizhiPei changed pull request status to merged Sep 26, 2025

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