hector-gr / RLCR-frontier-v2-sft-math

huggingface.co
Total runs: 18
24-hour runs: 0
7-day runs: 0
30-day runs: 13
Model's Last Updated: Février 28 2026
text-generation

Introduction of RLCR-frontier-v2-sft-math

Model Details of RLCR-frontier-v2-sft-math

Model Card for RLCR-frontier-v2-sft-math

This model is a fine-tuned version of mehuldamani/qwen-base-verifier-sft-v1 . 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="hector-gr/RLCR-frontier-v2-sft-math", 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: 4.0.0
  • 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 hector-gr RLCR-frontier-v2-sft-math on huggingface.co

18
Total runs
0
24-hour runs
2
3-day runs
0
7-day runs
13
30-day runs

More Information About RLCR-frontier-v2-sft-math huggingface.co Model

RLCR-frontier-v2-sft-math huggingface.co

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

RLCR-frontier-v2-sft-math huggingface.co Url

https://huggingface.co/hector-gr/RLCR-frontier-v2-sft-math

hector-gr RLCR-frontier-v2-sft-math online free

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

hector-gr RLCR-frontier-v2-sft-math online free url in huggingface.co:

https://huggingface.co/hector-gr/RLCR-frontier-v2-sft-math

RLCR-frontier-v2-sft-math install

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

RLCR-frontier-v2-sft-math install url in huggingface.co:

https://huggingface.co/hector-gr/RLCR-frontier-v2-sft-math

Url of RLCR-frontier-v2-sft-math

RLCR-frontier-v2-sft-math huggingface.co Url

Provider of RLCR-frontier-v2-sft-math huggingface.co

hector-gr
ORGANIZATIONS

Other API from hector-gr

huggingface.co

Total runs: 13
Run Growth: 8
Growth Rate: 66.67%
Updated:Février 23 2026