DiaLLM — Gemma 3-4B-it — en-UK — DPO

Built with Gemma.

Part of DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation (EMNLP 2026 Main).

DiaLLM pipeline

  • Base model: Gemma 3-4B-it
  • Target variety: en-UK (Northern British English)
  • Adaptation thread: explicit (variety-targeted)
  • Alignment method: DPO

Fine-tuned from jordanpainter/diallm-gemma-sft-brit via DPO with the target-variety preference pairs.

Code, checkpoints, preference datasets, linguistic-analysis toolkit: https://github.com/surrey-nlp/diallm

Paper: https://arxiv.org/abs/2607.07669

This model is a fine-tuned version of jordanpainter/diallm-gemma-sft-brit, trained using TRL.

Training procedure

This model was trained with DPO.

Framework versions

  • TRL: 0.28.0
  • Transformers: 4.57.6
  • Pytorch: 2.5.1+cu121
  • Datasets: 4.5.0
  • Tokenizers: 0.22.2

Citation

@article{painter2026diallm,
  title     = {DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation},
  author    = {Painter, Jordan and Srirag, Dipankar and Kappiyath, Adarsh and Kanojia, Diptesh and Joshi, Aditya and Yin, Lu},
  year      = {2026},
  eprint    = {2607.07669},
  archivePrefix = {arXiv}
}
@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},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}
}
@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}
}
Downloads last month
11
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jordanpainter/diallm-gemma-dpo-brit

Finetuned
(3)
this model

Collection including jordanpainter/diallm-gemma-dpo-brit

Paper for jordanpainter/diallm-gemma-dpo-brit