Instructions to use QizhiPei/ScaleDiff-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QizhiPei/ScaleDiff-7B with Transformers:

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

pipe = pipeline("text-generation", model="QizhiPei/ScaleDiff-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QizhiPei/ScaleDiff-7B")
model = AutoModelForCausalLM.from_pretrained("QizhiPei/ScaleDiff-7B")
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/ScaleDiff-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QizhiPei/ScaleDiff-7B"
# 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/ScaleDiff-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QizhiPei/ScaleDiff-7B

SGLang

How to use QizhiPei/ScaleDiff-7B 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/ScaleDiff-7B" \
    --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/ScaleDiff-7B",
		"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/ScaleDiff-7B" \
        --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/ScaleDiff-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QizhiPei/ScaleDiff-7B with Docker Model Runner:
```
docker model run hf.co/QizhiPei/ScaleDiff-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Paper: ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning

Code: https://github.com/QizhiPei/ScaleDiff

DiffScale-7B

This model is a fine-tuned version of QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k on the ScaleDiff-Math dataset.

Model description

ScaleDiff-7B is a Large Reasoning Model (LRM) developed as part of the ScaleDiff pipeline, which is designed to scale the creation of challenging mathematical problems. This model, fine-tuned on the novel ScaleDiff-Math dataset, aims to enhance advanced mathematical reasoning capabilities by addressing the scarcity of high-quality, difficult training data. It leverages an adaptive thinking model for problem identification and a specialized generator (DiffGen-8B) for large-scale problem synthesis.

Intended uses & limitations

ScaleDiff-7B is intended for advanced mathematical reasoning tasks, offering significant improvements in complex problem-solving. It is particularly useful for researchers and practitioners looking to benchmark and develop LRMs on difficult mathematical challenges.

Limitations: As a language model, its performance is dependent on the quality and scope of its training data. While designed for difficult problems, it may exhibit limitations in highly novel or out-of-distribution mathematical contexts. Further research is needed to fully understand its generalization capabilities beyond the specific benchmarks used in its evaluation.

Training and evaluation data

ScaleDiff-7B was fine-tuned on the custom-created ScaleDiff-Math dataset. This dataset is generated through a three-step pipeline:

Problem Selection: Difficult problems are identified from the AM-Distilled-Dataset using AdaptThink, an adaptive thinking model.
Problem Generation: A dedicated problem generator, DiffGen-8B, is trained on these selected difficult problems to produce new, challenging problems.
Solution Distillation and Filtration: Long Chain-of-Thought (CoT) solutions for the newly generated problems are distilled using Qwen3-8B as a teacher model and then filtered for quality and relevance.

The final ScaleDiff-Math dataset combines these new problem-solution pairs with an original dataset to provide a more effective training signal. Evaluation was conducted on a suite of difficult mathematical benchmarks including AIME'24, AIME'25, HMMT-Feb'25, BRUMO'25, and MATH500.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 32
total_eval_batch_size: 256
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0