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 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-Llama3.1-8B"
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'])
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}
}
OpenMath2-Llama3.1-8B-GGUF huggingface.co is an AI model on huggingface.co that provides OpenMath2-Llama3.1-8B-GGUF's model effect (), which can be used instantly with this QuantFactory OpenMath2-Llama3.1-8B-GGUF model. huggingface.co supports a free trial of the OpenMath2-Llama3.1-8B-GGUF model, and also provides paid use of the OpenMath2-Llama3.1-8B-GGUF. Support call OpenMath2-Llama3.1-8B-GGUF model through api, including Node.js, Python, http.
OpenMath2-Llama3.1-8B-GGUF huggingface.co is an online trial and call api platform, which integrates OpenMath2-Llama3.1-8B-GGUF's modeling effects, including api services, and provides a free online trial of OpenMath2-Llama3.1-8B-GGUF, you can try OpenMath2-Llama3.1-8B-GGUF online for free by clicking the link below.
QuantFactory OpenMath2-Llama3.1-8B-GGUF online free url in huggingface.co:
OpenMath2-Llama3.1-8B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find OpenMath2-Llama3.1-8B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of OpenMath2-Llama3.1-8B-GGUF install, users can directly use OpenMath2-Llama3.1-8B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
OpenMath2-Llama3.1-8B-GGUF install url in huggingface.co: