Instructions to use sail/Qwen2.5-Math-7B-Oat-Zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sail/Qwen2.5-Math-7B-Oat-Zero with Transformers:

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

pipe = pipeline("text-generation", model="sail/Qwen2.5-Math-7B-Oat-Zero")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sail/Qwen2.5-Math-7B-Oat-Zero")
model = AutoModelForCausalLM.from_pretrained("sail/Qwen2.5-Math-7B-Oat-Zero")
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 Settings

vLLM

How to use sail/Qwen2.5-Math-7B-Oat-Zero with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sail/Qwen2.5-Math-7B-Oat-Zero"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sail/Qwen2.5-Math-7B-Oat-Zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sail/Qwen2.5-Math-7B-Oat-Zero

SGLang

How to use sail/Qwen2.5-Math-7B-Oat-Zero 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 "sail/Qwen2.5-Math-7B-Oat-Zero" \
    --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": "sail/Qwen2.5-Math-7B-Oat-Zero",
		"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 "sail/Qwen2.5-Math-7B-Oat-Zero" \
        --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": "sail/Qwen2.5-Math-7B-Oat-Zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sail/Qwen2.5-Math-7B-Oat-Zero with Docker Model Runner:
```
docker model run hf.co/sail/Qwen2.5-Math-7B-Oat-Zero
```

Add question-answering pipeline tag and link to Hugging Face paper

by nielsr HF Staff - opened Mar 27, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-8

Files changed (1) hide show

README.md +16 -8

README.md CHANGED Viewed

@@ -1,15 +1,16 @@
 ---
-library_name: transformers
-license: apache-2.0
 base_model:
 - Qwen/Qwen2.5-Math-7B
 ---
 # Qwen2.5-Math-7B-Oat-Zero
 ## Links
-- 📜 [Paper](https://github.com/sail-sg/understand-r1-zero/blob/main/understand-r1-zero.pdf)
 - 💻 [GitHub](https://github.com/sail-sg/understand-r1-zero)
 - 🤗 [Oat-Zero Collection](https://huggingface.co/collections/sail/oat-zero-understanding-r1-zero-like-training-67dcdb07b9f3eb05f1501c4a)
@@ -33,17 +34,24 @@ import vllm
 def apply_qwen_math_template(question: str):
     return (
-        "<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n<|im_start|>user\n"
         + question
-        + "<|im_end|>\n<|im_start|>assistant\n"
     )
 def apply_r1_template(question: str):
     return (
         "A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. "
-        "The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.\nUser: "
         + question
-        + "\nAssistant: <think>"
     )
 model_name = "sail/Qwen2.5-Math-7B-Oat-Zero"
@@ -85,4 +93,4 @@ print(outputs)
   year={2025},
   howpublished={\url{https://github.com/sail-sg/understand-r1-zero}},
 }
-```

 ---
 base_model:
 - Qwen/Qwen2.5-Math-7B
+library_name: transformers
+license: apache-2.0
+pipeline_tag: question-answering
 ---
 # Qwen2.5-Math-7B-Oat-Zero
 ## Links
+- 📜 [Paper](https://huggingface.co/papers/2503.20783)
 - 💻 [GitHub](https://github.com/sail-sg/understand-r1-zero)
 - 🤗 [Oat-Zero Collection](https://huggingface.co/collections/sail/oat-zero-understanding-r1-zero-like-training-67dcdb07b9f3eb05f1501c4a)
 def apply_qwen_math_template(question: str):
     return (
+        "<|im_start|>system
+Please reason step by step, and put your final answer within \\boxed{}.<|im_end|>
+<|im_start|>user
+"
         + question
+        + "<|im_end|>
+<|im_start|>assistant
+"
     )
 def apply_r1_template(question: str):
     return (
         "A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. "
+        "The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.
+User: "
         + question
+        + "
+Assistant: <think>"
     )
 model_name = "sail/Qwen2.5-Math-7B-Oat-Zero"
   year={2025},
   howpublished={\url{https://github.com/sail-sg/understand-r1-zero}},
 }
+```