mehuldamani / big-math-digits-v2-correctness

huggingface.co
Total runs: 446
24-hour runs: 5
7-day runs: 34
30-day runs: 416
Model's Last Updated: June 26 2025
text-generation

Introduction of big-math-digits-v2-correctness

Model Details of big-math-digits-v2-correctness

Model Card for big-math-digits-v2-correctness

This model is a fine-tuned version of Qwen/Qwen2.5-7B . It has been trained using TRL .

Quick start
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="mehuldamani/big-math-digits-v2-correctness", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
Training procedure

Visualize in Weights & Biases

This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models .

Framework versions
  • TRL: 0.16.0.dev0
  • Transformers: 4.48.3
  • Pytorch: 2.5.1
  • Datasets: 3.6.0
  • Tokenizers: 0.21.1
Citations

Cite GRPO as:

@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Runs of mehuldamani big-math-digits-v2-correctness on huggingface.co

446
Total runs
5
24-hour runs
11
3-day runs
34
7-day runs
416
30-day runs

More Information About big-math-digits-v2-correctness huggingface.co Model

big-math-digits-v2-correctness huggingface.co

big-math-digits-v2-correctness huggingface.co is an AI model on huggingface.co that provides big-math-digits-v2-correctness's model effect (), which can be used instantly with this mehuldamani big-math-digits-v2-correctness model. huggingface.co supports a free trial of the big-math-digits-v2-correctness model, and also provides paid use of the big-math-digits-v2-correctness. Support call big-math-digits-v2-correctness model through api, including Node.js, Python, http.

big-math-digits-v2-correctness huggingface.co Url

https://huggingface.co/mehuldamani/big-math-digits-v2-correctness

mehuldamani big-math-digits-v2-correctness online free

big-math-digits-v2-correctness huggingface.co is an online trial and call api platform, which integrates big-math-digits-v2-correctness's modeling effects, including api services, and provides a free online trial of big-math-digits-v2-correctness, you can try big-math-digits-v2-correctness online for free by clicking the link below.

mehuldamani big-math-digits-v2-correctness online free url in huggingface.co:

https://huggingface.co/mehuldamani/big-math-digits-v2-correctness

big-math-digits-v2-correctness install

big-math-digits-v2-correctness is an open source model from GitHub that offers a free installation service, and any user can find big-math-digits-v2-correctness on GitHub to install. At the same time, huggingface.co provides the effect of big-math-digits-v2-correctness install, users can directly use big-math-digits-v2-correctness installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

big-math-digits-v2-correctness install url in huggingface.co:

https://huggingface.co/mehuldamani/big-math-digits-v2-correctness

Url of big-math-digits-v2-correctness

big-math-digits-v2-correctness huggingface.co Url

Provider of big-math-digits-v2-correctness huggingface.co

mehuldamani
ORGANIZATIONS

Other API from mehuldamani