Openmath2 Llama3.1 70B

🚀 OpenMath2-Llama3.1-70B

OpenMath2-Llama3.1-70B is a model that addresses the need for high - performance in mathematical problem - solving. It is obtained by finetuning Llama3.1-70B-Base with OpenMathInstruct-2, offering enhanced mathematical capabilities compared to its base model.

🚀 Quick Start

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%.

✨ Features

Performance Comparison

Open - Source Resources

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

• Code
• Models
• Dataset

💻 Usage Examples

Basic Usage

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'])

📚 Documentation

Model Details

Usage Notes

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.

Reproducing Results

We provide all instructions to fully reproduce our results.

📄 License

By accessing this model, you are agreeing to the LLama 3.1 terms and conditions of the license, acceptable use policy and Meta’s privacy policy

📚 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}
}

⚠️ Important Note

These models have NOT been instruction - tuned on general data and thus might not provide good answers outside of the math domain.

💡 Usage Tip

We recommend using instructions in our repo to run inference with these models.