# Incremental Training using run\_mlm.py

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fincremental-training-using-run-mlm-py%2F27677%3E%5C
**Category:** 🤗Transformers\
**Created:** [December 12, 2022, 6:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fincremental-training-using-run-mlm-py%2F27677 "2022-12-12T06:35:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mlpsycho](https://avatars.discourse-cdn.com/v4/letter/m/b5e925/32.png) [@mlpsycho](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmlpsycho)%5C
**Post date:** [December 12, 2022, 6:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fincremental-training-using-run-mlm-py%2F27677%2F1 "2022-12-12T06:35:03Z")

</div>

I trained a model using a pre-trained model albert-base-v2 and my own domain dataset. After that I got the new model and tokenizers. Now I want to use this trained model and tokenizer instead of initial ones. How can I load this model and tokenizers using run\_mlm.py