Quantization made by Richard Erkhov.

Qwen2-0.5B-NashMD - GGUF

Model creator: https://huggingface.co/qgallouedec/
Original model: https://huggingface.co/qgallouedec/Qwen2-0.5B-NashMD/

Name	Quant method	Size
Qwen2-0.5B-NashMD.Q2_K.gguf	Q2_K	0.32GB
Qwen2-0.5B-NashMD.IQ3_XS.gguf	IQ3_XS	0.32GB
Qwen2-0.5B-NashMD.IQ3_S.gguf	IQ3_S	0.32GB
Qwen2-0.5B-NashMD.Q3_K_S.gguf	Q3_K_S	0.32GB
Qwen2-0.5B-NashMD.IQ3_M.gguf	IQ3_M	0.32GB
Qwen2-0.5B-NashMD.Q3_K.gguf	Q3_K	0.33GB
Qwen2-0.5B-NashMD.Q3_K_M.gguf	Q3_K_M	0.33GB
Qwen2-0.5B-NashMD.Q3_K_L.gguf	Q3_K_L	0.34GB
Qwen2-0.5B-NashMD.IQ4_XS.gguf	IQ4_XS	0.33GB
Qwen2-0.5B-NashMD.Q4_0.gguf	Q4_0	0.33GB
Qwen2-0.5B-NashMD.IQ4_NL.gguf	IQ4_NL	0.33GB
Qwen2-0.5B-NashMD.Q4_K_S.gguf	Q4_K_S	0.36GB
Qwen2-0.5B-NashMD.Q4_K.gguf	Q4_K	0.37GB
Qwen2-0.5B-NashMD.Q4_K_M.gguf	Q4_K_M	0.37GB
Qwen2-0.5B-NashMD.Q4_1.gguf	Q4_1	0.35GB
Qwen2-0.5B-NashMD.Q5_0.gguf	Q5_0	0.37GB
Qwen2-0.5B-NashMD.Q5_K_S.gguf	Q5_K_S	0.38GB
Qwen2-0.5B-NashMD.Q5_K.gguf	Q5_K	0.39GB
Qwen2-0.5B-NashMD.Q5_K_M.gguf	Q5_K_M	0.39GB
Qwen2-0.5B-NashMD.Q5_1.gguf	Q5_1	0.39GB
Qwen2-0.5B-NashMD.Q6_K.gguf	Q6_K	0.47GB
Qwen2-0.5B-NashMD.Q8_0.gguf	Q8_0	0.49GB

Original model description:

base_model: Qwen/Qwen2-0.5B-Instruct library_name: transformers model_name: Qwen2-0.5B-NashMD tags: - generated_from_trainer - trl - nash-md licence: license

Model Card for Qwen2-0.5B-NashMD

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct. 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="qgallouedec/Qwen2-0.5B-NashMD", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with Nash-MD, a method introduced in Nash Learning from Human Feedback.

Framework versions

TRL: 0.12.0.dev0
Transformers: 4.46.0.dev0
Pytorch: 2.4.1
Datasets: 3.0.2
Tokenizers: 0.20.0

Citations

Cite Nash-MD as:

@inproceedings{munos2024nash,
    title        = {Nash Learning from Human Feedback},
    author       = {R{'{e}}mi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and C{\^{o}}me Fiegel and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},
    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=Y5AmNYiyCQ}
}

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}}
}