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

Libraries

How to use QizhiPei/DeepSeekMath-7B-MathFusion with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/QizhiPei/DeepSeekMath-7B-MathFusion

SGLang

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

Docker Model Runner
How to use QizhiPei/DeepSeekMath-7B-MathFusion with Docker Model Runner:
```
docker model run hf.co/QizhiPei/DeepSeekMath-7B-MathFusion
```

Add pipeline tag, library, license and link to code

by nielsr HF Staff - opened Mar 21, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +9 -3

README.md CHANGED Viewed

@@ -1,11 +1,17 @@
 ---
 datasets:
 - QizhiPei/MathFusionQA
 language:
 - en
-base_model:
-- deepseek-ai/deepseek-math-7b-base
 ---
-Paper: [MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion](https://arxiv.org/abs/2503.16212)

 ---
+base_model:
+- deepseek-ai/deepseek-math-7b-base
 datasets:
 - QizhiPei/MathFusionQA
 language:
 - en
+pipeline_tag: question-answering
+library_name: transformers
+license: mit
 ---
+Paper: [MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion](https://arxiv.org/abs/2503.16212)
+This model, `DeepSeekMath-7B-MathFusion`, is a fine-tuned version of `deepseek-ai/deepseek-math-7b-base` trained on the `QizhiPei/MathFusionQA` dataset. It's designed for question-answering tasks, particularly in the domain of mathematics.
+Code: https://github.com/QizhiPei/MathFusion