# Tokenizer effect on the fine-tuning

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-effect-on-the-fine-tuning%2F57650%3E%5C
**Category:** Research\
**Created:** [October 6, 2023, 5:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-effect-on-the-fine-tuning%2F57650 "2023-10-06T17:19:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![alielfilali01](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/alielfilali01/32/59086_2.png) [@alielfilali01](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falielfilali01)%5C
**Post date:** [October 6, 2023, 5:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-effect-on-the-fine-tuning%2F57650%2F1 "2023-10-06T17:19:06Z")

</div>

Hi everyone, I’m on a project to fine-tune multiple 7B and less text2text generation models on arabic and i was wondering about the effect of the original tokenizer on the fine tuning process or what if i use a tokenizer different from the model’s original one! Let’s say BLOOM tokenizer, Will that hurts the model’s performance? So if anyone have seen a paper to discuss this or something similar please drop it here it will be really beneficial or simply comment your thoughts 🙏🏻