---

base_model:

• MRockatansky/Gemma-4-31B-storymaxxed2

language:

• en

license: apache-2.0

quantized_by: MRockatansky

tags:

• text-generation
• dpo
• creative-writing

---

Model Card for Gemma-4-31B-storymaxxed2

This model is a fine-tuned version of trohrbaugh/gemma-4-31b-it-heretic-ara.

It has been trained using TRL. Optimized specifically for creative writing and narrative prose.

Training procedure

This model was trained with TRL using DPO on a high quality dataset of narrative preference pairs. It was LoRa trained

on over 5,000 pairs for 8 hours.

Introduction to training method used:

Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Recommended Sampler Settings

For optimal inference, use the standard generation parameters recommended by Google for Gemma-4 models:

- Temperature - 1.0

- Top P - 0.95

- Top K - 64

Vision mmproj

The mmproj file for vision can be found here: https://huggingface.co/MRockatansky/Gemma-4-31B-storymaxxed2-GGUF

Range of quants courtesy of mradermacher: https://huggingface.co/mradermacher/Gemma-4-31B-storymaxxed2-i1-GGUF

Framework versions

• PEFT 0.19.1
• TRL: 1.4.0
• Transformers: 5.9.0
• Pytorch: 2.11.0+cu130
• Datasets: 4.8.5
• Tokenizers: 0.22.2

Citations

Cite DPO as:

@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
    year         = 2023,
    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}