# Does tokenizer changed during model training
**URL:**
**Author:**  [@Talha](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTalha)%5C
**Post date:** [June 15, 2022, 7:01pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-changed-during-model-training%2F19213%2F1 "2022-06-15T19:01:15Z")
I want to know during model training, does tokenizer alter it self, (i mean does it train) or it remain the same as original one.
For example i used the
`AutoTokenizer.from_pretrained(model_name,local_files_only=False)`
after model training, is there any change to tokenizer?
---
**Author:**  [@Slinae](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSlinae)%5C
**Post date:** [June 16, 2022, 1:44am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-changed-during-model-training%2F19213%2F2 "2022-06-16T01:44:22Z")
Hi, Talha,
Tokenizer id does not change. For example, the token\_id of `[['sep']]` is 102. It will be 102 through the training. But the embedding hidden state will be changed.
---
**Author:**  [@ShieldHero](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FShieldHero)%5C
**Post date:** [August 11, 2022, 1:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdoes-tokenizer-changed-during-model-training%2F19213%2F3 "2022-08-11T13:47:47Z")
One doubt. So lets say I have trained two models of “bert-base-uncased” to do different classification tasks(same number of classes).
So, now, can I use the tokenizer of one model1 to tokenize the other one? Will the result be different compared to using two different tokenizers?