Instructions to use nvidia/OpenMath-CodeLlama-70b-Python-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/OpenMath-CodeLlama-70b-Python-hf with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/OpenMath-CodeLlama-70b-Python-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenMath-CodeLlama-70b-Python-hf")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenMath-CodeLlama-70b-Python-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/OpenMath-CodeLlama-70b-Python-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/OpenMath-CodeLlama-70b-Python-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/OpenMath-CodeLlama-70b-Python-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nvidia/OpenMath-CodeLlama-70b-Python-hf

SGLang

How to use nvidia/OpenMath-CodeLlama-70b-Python-hf 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/OpenMath-CodeLlama-70b-Python-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/OpenMath-CodeLlama-70b-Python-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/OpenMath-CodeLlama-70b-Python-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/OpenMath-CodeLlama-70b-Python-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

OpenMath-CodeLlama-70b-Python-hf

OpenMath models were designed to solve mathematical problems by integrating text-based reasoning with code blocks executed by Python interpreter. The models were trained on OpenMathInstruct-1, a math instruction tuning dataset with 1.8M problem-solution pairs generated using permissively licensed Mixtral-8x7B model.

	greedy		majority@50
model	GSM8K	MATH	GMS8K	MATH
OpenMath-CodeLlama-7B (nemo \| HF)	75.9	43.6	84.8	55.6
OpenMath-Mistral-7B (nemo \| HF)	80.2	44.5	86.9	57.2
OpenMath-CodeLlama-13B (nemo \| HF)	78.8	45.5	86.8	57.6
OpenMath-CodeLlama-34B (nemo \| HF)	80.7	48.3	88.0	60.2
OpenMath-Llama2-70B (nemo \| HF)	84.7	46.3	90.1	58.3
OpenMath-CodeLlama-70B (nemo \| HF)	84.6	50.7	90.8	60.4

The pipeline we used to produce these models is fully open-sourced!

See our paper for more details!

How to use the models?

Try to run inference with our models with just a few commands!

Reproducing our results

We provide all instructions to fully reproduce our results.

Improving other models

To improve other models or to learn more about our code, read through the docs below.

NeMo-Skills Pipeline

In our pipeline we use NVIDIA NeMo, an end-to-end, cloud-native framework to build, customize, and deploy generative AI models anywhere. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

Citation

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

@article{toshniwal2024openmath,
  title   = {OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset},
  author  = {Shubham Toshniwal and Ivan Moshkov and Sean Narenthiran and Daria Gitman and Fei Jia and Igor Gitman},
  year    = {2024},
  journal = {arXiv preprint arXiv: Arxiv-2402.10176}
}