Instructions to use nvidia/OpenMath2-Llama3.1-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/OpenMath2-Llama3.1-70B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/OpenMath2-Llama3.1-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenMath2-Llama3.1-70B")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenMath2-Llama3.1-70B")
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 nvidia/OpenMath2-Llama3.1-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/OpenMath2-Llama3.1-70B"
# 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-Llama3.1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/OpenMath2-Llama3.1-70B

SGLang

How to use nvidia/OpenMath2-Llama3.1-70B 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-Llama3.1-70B" \
    --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-Llama3.1-70B",
		"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-Llama3.1-70B" \
        --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-Llama3.1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/OpenMath2-Llama3.1-70B with Docker Model Runner:
```
docker model run hf.co/nvidia/OpenMath2-Llama3.1-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenMath2-Llama3.1-70B

OpenMath2-Llama3.1-70B is obtained by finetuning Llama3.1-70B-Base with OpenMathInstruct-2.

The model outperforms Llama3.1-70B-Instruct on MATH by 3.9%.

Model	GSM8K	MATH	AMC 2023	AIME 2024	Omni-MATH
Llama3.1-8B-Instruct	84.5	51.9	9/40	2/30	12.7
OpenMath2-Llama3.1-8B (nemo \| HF)	91.7	67.8	16/40	3/30	22.0
+ majority@256	94.1	76.1	23/40	3/30	24.6
Llama3.1-70B-Instruct	95.8	67.9	19/40	6/30	19.0
OpenMath2-Llama3.1-70B (nemo \| HF)	94.9	71.9	20/40	4/30	23.1
+ majority@256	96.0	79.6	24/40	6/30	27.6

The pipeline we used to produce the data and models is fully open-sourced!

See our paper to learn more details!

How to use the models?

Our models are trained with the same "chat format" as Llama3.1-instruct models (same system/user/assistant tokens). Please note that these models have NOT been instruction-tuned on general data and thus might not provide good answers outside of the math domain.

We recommend using instructions in our repo to run inference with these models, but here is an example of how to do it through transformers api:

import transformers
import torch

model_id = "nvidia/OpenMath2-Llama3.1-70B"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

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 $a^2+6a-7$?"},
]

outputs = pipeline(
    messages,
    max_new_tokens=4096,
)
print(outputs[0]["generated_text"][-1]['content'])

Reproducing our results

We provide all instructions to fully reproduce our results.

Citation

If you find our work useful, please consider citing us!

@article{toshniwal2024openmath2,
  title   = {OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data},
  author  = {Shubham Toshniwal and Wei Du and Ivan Moshkov and  Branislav Kisacanin and Alexan Ayrapetyan and Igor Gitman},
  year    = {2024},
  journal = {arXiv preprint arXiv:2410.01560}
}