QuantFactory / OpenMath2-Llama3.1-8B-GGUF

huggingface.co
Total runs: 1.2K
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: October 05 2024

Introduction of OpenMath2-Llama3.1-8B-GGUF

Model Details of OpenMath2-Llama3.1-8B-GGUF

QuantFactory Banner

QuantFactory/OpenMath2-Llama3.1-8B-GGUF

This is quantized version of nvidia/OpenMath2-Llama3.1-8B created using llama.cpp

Original Model Card

OpenMath2-Llama3.1-8B

OpenMath2-Llama3.1-8B is obtained by finetuning Llama3.1-8B-Base with OpenMathInstruct-2 .

The model outperforms Llama3.1-8B-Instruct on all the popular math benchmarks we evaluate on, especially on MATH by 15.9%.

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 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'])

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}
}
Terms of use

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

Runs of QuantFactory OpenMath2-Llama3.1-8B-GGUF on huggingface.co

1.2K
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About OpenMath2-Llama3.1-8B-GGUF huggingface.co Model

More OpenMath2-Llama3.1-8B-GGUF license Visit here:

https://choosealicense.com/licenses/llama3.1

OpenMath2-Llama3.1-8B-GGUF huggingface.co

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 Url

https://huggingface.co/QuantFactory/OpenMath2-Llama3.1-8B-GGUF

QuantFactory OpenMath2-Llama3.1-8B-GGUF online free

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:

https://huggingface.co/QuantFactory/OpenMath2-Llama3.1-8B-GGUF

OpenMath2-Llama3.1-8B-GGUF install

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:

https://huggingface.co/QuantFactory/OpenMath2-Llama3.1-8B-GGUF

Url of OpenMath2-Llama3.1-8B-GGUF

OpenMath2-Llama3.1-8B-GGUF huggingface.co Url

Provider of OpenMath2-Llama3.1-8B-GGUF huggingface.co

QuantFactory
ORGANIZATIONS

Other API from QuantFactory