Instructions to use nvidia/OpenMath2-Llama3.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/OpenMath2-Llama3.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/OpenMath2-Llama3.1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenMath2-Llama3.1-8B")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenMath2-Llama3.1-8B", device_map="auto")
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 nvidia/OpenMath2-Llama3.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/OpenMath2-Llama3.1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/OpenMath2-Llama3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/OpenMath2-Llama3.1-8B

SGLang

How to use nvidia/OpenMath2-Llama3.1-8B 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 "nvidia/OpenMath2-Llama3.1-8B" \
    --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": "nvidia/OpenMath2-Llama3.1-8B",
		"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 "nvidia/OpenMath2-Llama3.1-8B" \
        --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": "nvidia/OpenMath2-Llama3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/OpenMath2-Llama3.1-8B with Docker Model Runner:
```
docker model run hf.co/nvidia/OpenMath2-Llama3.1-8B
```

Add pipeline tag and link to OpenCodeReasoning paper

by nielsr HF Staff - opened Apr 6, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-5

Files changed (1) hide show

README.md +8 -5

README.md CHANGED Viewed

@@ -1,22 +1,23 @@
 ---
-license: llama3.1
 base_model:
 - meta-llama/Llama-3.1-8B
 datasets:
 - nvidia/OpenMathInstruct-2
 language:
 - en
 tags:
 - nvidia
 - math
-library_name: transformers
 ---
 # OpenMath2-Llama3.1-8B
-OpenMath2-Llama3.1-8B is obtained by finetuning [Llama3.1-8B-Base](https://huggingface.co/meta-llama/Llama-3.1-8B) with [OpenMathInstruct-2](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2).
-The model outperforms [Llama3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on all the popular math benchmarks we evaluate on, especially on [MATH](https://github.com/hendrycks/math) by 15.9%.
 <!-- <p align="center">
   <img src="scaling_plot.jpg" width="350"><img src="math_level_comp.jpg" width="350">
@@ -81,7 +82,9 @@ pipeline = transformers.pipeline(
 messages = [
     {
         "role": "user",
-        "content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\n" +
         "What is the minimum value of $a^2+6a-7$?"},
 ]

 ---
 base_model:
 - meta-llama/Llama-3.1-8B
 datasets:
 - nvidia/OpenMathInstruct-2
 language:
 - en
+library_name: transformers
+license: llama3.1
+pipeline_tag: text-generation
 tags:
 - nvidia
 - math
 ---
 # OpenMath2-Llama3.1-8B
+OpenMath2-Llama3.1-8B is obtained by finetuning [Llama3.1-8B-Base](https://huggingface.co/meta-llama/Llama-3.1-8B) with [OpenMathInstruct-2](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2). This model is described in the paper [OpenCodeReasoning: Advancing Data Distillation for Competitive Coding](https://huggingface.co/papers/2504.01943).
+The model outperforms [Llama3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on all the popular math benchmarks we evaluate on, especially on [MATH](https://github.com/hendrycks/math) by 15.9%.
 <!-- <p align="center">
   <img src="scaling_plot.jpg" width="350"><img src="math_level_comp.jpg" width="350">
 messages = [
     {
         "role": "user",
+        "content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.
+" +
         "What is the minimum value of $a^2+6a-7$?"},
 ]