Instructions to use Intel/deepmath-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/deepmath-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Intel/deepmath-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/deepmath-v1")
model = AutoModelForCausalLM.from_pretrained("Intel/deepmath-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intel/deepmath-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Intel/deepmath-v1

SGLang

How to use Intel/deepmath-v1 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 "Intel/deepmath-v1" \
    --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": "Intel/deepmath-v1",
		"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 "Intel/deepmath-v1" \
        --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": "Intel/deepmath-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intel/deepmath-v1 with Docker Model Runner:
```
docker model run hf.co/Intel/deepmath-v1
```

danf commited on Nov 20, 2025

Commit

f35ce4b

verified ·

1 Parent(s): 7a7885d

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -18,13 +18,13 @@ library_name: transformers
 pipeline_tag: text-generation
 ---
-# DeepMath-v1: A Lightweight Math Reasoning Agent
 <img src="https://cdn-uploads.huggingface.co/production/uploads/62d93cd728f9c86a4031562e/ndb_WmPavW1MONAjsGpYT.jpeg" style="width:600px" alt="An LLM is using a calculator to answer questions." />
 ## Model Description
-**DeepMath-v1** is a 4B parameter mathematical reasoning model that combines a fine-tuned LLM with a sandboxed Python executor. Built on [Qwen3-4B Thinking](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) and trained with **GRPO (Group Relative Policy Optimization)**, DeepMath generates concise Python snippets for computational steps instead of verbose text explanations, significantly reducing errors and output length.
 - **Developed by:** Intel AI Labs
 - **Model type:** Causal language model with agent capabilities
@@ -43,7 +43,7 @@ pipeline_tag: text-generation
 ## Model Architecture
-DeepMath-v1 uses a LoRA adapter fine-tuned on top of Qwen3-4B Thinking with the following components:
 - **Agent Interface:** Outputs special tokens for Python code execution during reasoning
 - **Executor:** Sandboxed Python environment with allow-listed modules

 pipeline_tag: text-generation
 ---
+# DeepMath: A Lightweight Math Reasoning Agent
 <img src="https://cdn-uploads.huggingface.co/production/uploads/62d93cd728f9c86a4031562e/ndb_WmPavW1MONAjsGpYT.jpeg" style="width:600px" alt="An LLM is using a calculator to answer questions." />
 ## Model Description
+**DeepMath** is a 4B parameter mathematical reasoning model that combines a fine-tuned LLM with a sandboxed Python executor. Built on [Qwen3-4B Thinking](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) and trained with **GRPO (Group Relative Policy Optimization)**, DeepMath generates concise Python snippets for computational steps instead of verbose text explanations, significantly reducing errors and output length.
 - **Developed by:** Intel AI Labs
 - **Model type:** Causal language model with agent capabilities
 ## Model Architecture
+DeepMath uses a LoRA adapter fine-tuned on top of Qwen3-4B Thinking with the following components:
 - **Agent Interface:** Outputs special tokens for Python code execution during reasoning
 - **Executor:** Sandboxed Python environment with allow-listed modules