# BART finetuning for summarization without seq2seq trainer

**URL:** <https://discuss.huggingface.co/t/bart-finetuning-for-summarization-without-seq2seq-trainer/25195>\
**Category:** Beginners\
**Created:** [October 29, 2022, 4:31pm UTC](https://discuss.huggingface.co/t/bart-finetuning-for-summarization-without-seq2seq-trainer/25195 "2022-10-29T16:31:01Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mse30](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@mse30](https://discuss.huggingface.co/u/mse30)\
**Post date:** [October 29, 2022, 4:31pm UTC](https://discuss.huggingface.co/t/bart-finetuning-for-summarization-without-seq2seq-trainer/25195/1 "2022-10-29T16:31:01Z")

</div>

Hello, I am looking for an example code for BART finetuning with huggingface (not fairseq) without the seq2seq trainer  
Any guidance here?

---

<div class="post-metadata">

**Author:** ![thies](https://avatars.discourse-cdn.com/v4/letter/t/ed655f/32.png) [@thies](https://discuss.huggingface.co/u/thies)\
**Post date:** [October 31, 2022, 8:19am UTC](https://discuss.huggingface.co/t/bart-finetuning-for-summarization-without-seq2seq-trainer/25195/2 "2022-10-31T08:19:40Z")

</div>

Maybe you can tgry this one:

> <https://github.com/huggingface/transformers/blob/main/examples/pytorch/summarization/run_summarization_no_trainer.py>