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
```

Improve model card: Add pipeline tag, update license and expand descriptions

by nielsr HF Staff - opened Sep 26, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+15

-11

Files changed (1) hide show

README.md +15 -11

README.md CHANGED Viewed

@@ -1,38 +1,43 @@
 ---
-library_name: transformers
-license: other
 base_model: QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k
 tags:
 - llama-factory
 - full
 - generated_from_trainer
 model-index:
 - name: DiffScale-7B
   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. -->
 Paper: [ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning](https://arxiv.org/abs/2509.21070)
 Code: https://github.com/QizhiPei/ScaleDiff
 # DiffScale-7B
-This model is a fine-tuned version of [QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k](https://huggingface.co/QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k) on the DiffScale-Math dataset.
 ## Model description
-More information needed
 ## Intended uses & limitations
-More information needed
 ## Training and evaluation data
-More information needed
 ## Training procedure
@@ -61,5 +66,4 @@ The following hyperparameters were used during training:
 - Transformers 4.46.1
 - Pytorch 2.4.0+cu121
 - Datasets 3.1.0
-- Tokenizers 0.20.3

 ---
 base_model: QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k
+library_name: transformers
+license: apache-2.0
 tags:
 - llama-factory
 - full
 - generated_from_trainer
+pipeline_tag: text-generation
 model-index:
 - name: DiffScale-7B
   results: []
 ---
 Paper: [ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning](https://arxiv.org/abs/2509.21070)
 Code: https://github.com/QizhiPei/ScaleDiff
 # DiffScale-7B
+This model is a fine-tuned version of [QizhiPei/Qwen2.5-Math-7B-Instruct-RoPE-300k](https://huggingface.co/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](https://huggingface.co/datasets/QizhiPei/ScaleDiff-Math). This dataset is generated through a three-step pipeline:
+1.  **Problem Selection**: Difficult problems are identified from the [AM-Distilled-Dataset](https://huggingface.co/datasets/a-m-team/AM-Qwen3-Distilled) using AdaptThink, an adaptive thinking model.
+2.  **Problem Generation**: A dedicated problem generator, DiffGen-8B, is trained on these selected difficult problems to produce new, challenging problems.
+3.  **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
 - Transformers 4.46.1
 - Pytorch 2.4.0+cu121
 - Datasets 3.1.0
+- Tokenizers 0.20.3