igorktech / Skommarkhos-7b-ARPO-v5

huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 16 2025

Introduction of Skommarkhos-7b-ARPO-v5

Model Details of Skommarkhos-7b-ARPO-v5

Model Card for skommarkhos-lucie7binstructv1-1-sft-arpo-a5

This model is a fine-tuned version of OpenLLM-France/Lucie-7B-Instruct-v1.1 . 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="igorktech/skommarkhos-lucie7binstructv1-1-sft-arpo-a5", 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 CPO, a method introduced in Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation .

Framework versions
  • TRL: 0.18.2
  • Transformers: 4.52.4
  • Pytorch: 2.7.0
  • Datasets: 3.6.0
  • Tokenizers: 0.21.1
Citations

Cite CPO as:

@inproceedings{xu2024contrastive,
    title        = {{Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}},
    author       = {Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
    year         = 2024,
    booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
    publisher    = {OpenReview.net},
    url          = {https://openreview.net/forum?id=51iwkioZpn}
}

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 Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Runs of igorktech Skommarkhos-7b-ARPO-v5 on huggingface.co

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

More Information About Skommarkhos-7b-ARPO-v5 huggingface.co Model

Skommarkhos-7b-ARPO-v5 huggingface.co

Skommarkhos-7b-ARPO-v5 huggingface.co is an AI model on huggingface.co that provides Skommarkhos-7b-ARPO-v5's model effect (), which can be used instantly with this igorktech Skommarkhos-7b-ARPO-v5 model. huggingface.co supports a free trial of the Skommarkhos-7b-ARPO-v5 model, and also provides paid use of the Skommarkhos-7b-ARPO-v5. Support call Skommarkhos-7b-ARPO-v5 model through api, including Node.js, Python, http.

Skommarkhos-7b-ARPO-v5 huggingface.co Url

https://huggingface.co/igorktech/Skommarkhos-7b-ARPO-v5

igorktech Skommarkhos-7b-ARPO-v5 online free

Skommarkhos-7b-ARPO-v5 huggingface.co is an online trial and call api platform, which integrates Skommarkhos-7b-ARPO-v5's modeling effects, including api services, and provides a free online trial of Skommarkhos-7b-ARPO-v5, you can try Skommarkhos-7b-ARPO-v5 online for free by clicking the link below.

igorktech Skommarkhos-7b-ARPO-v5 online free url in huggingface.co:

https://huggingface.co/igorktech/Skommarkhos-7b-ARPO-v5

Skommarkhos-7b-ARPO-v5 install

Skommarkhos-7b-ARPO-v5 is an open source model from GitHub that offers a free installation service, and any user can find Skommarkhos-7b-ARPO-v5 on GitHub to install. At the same time, huggingface.co provides the effect of Skommarkhos-7b-ARPO-v5 install, users can directly use Skommarkhos-7b-ARPO-v5 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Skommarkhos-7b-ARPO-v5 install url in huggingface.co:

https://huggingface.co/igorktech/Skommarkhos-7b-ARPO-v5

Url of Skommarkhos-7b-ARPO-v5

Skommarkhos-7b-ARPO-v5 huggingface.co Url

Provider of Skommarkhos-7b-ARPO-v5 huggingface.co

igorktech
ORGANIZATIONS

Other API from igorktech

huggingface.co

Total runs: 129
Run Growth: 119
Growth Rate: 93.70%
Updated:January 18 2024
huggingface.co

Total runs: 24
Run Growth: 23
Growth Rate: 100.00%
Updated:September 14 2026
huggingface.co

Total runs: 20
Run Growth: 0
Growth Rate: 0.00%
Updated:August 06 2025
huggingface.co

Total runs: 16
Run Growth: 0
Growth Rate: 0.00%
Updated:August 06 2025
huggingface.co

Total runs: 13
Run Growth: 0
Growth Rate: 0.00%
Updated:August 06 2025
huggingface.co

Total runs: 11
Run Growth: 7
Growth Rate: 63.64%
Updated:February 01 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:October 29 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:October 30 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 06 2025