# Load fine tuned model from local
**URL:**
**Author:**  [@datistiquo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdatistiquo)%5C
**Post date:** [October 20, 2020, 1:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-from-local%2F1651%2F1 "2020-10-20T13:25:34Z")
Hey,
if I fine tune a BERT model is the tokneizer somehow affected?
If I save my finetuned model like:
bert\_model.save\_pretrained(’./Fine\_tune\_BERT/’)
is the tokenizer saved too? is the tokenizer modified? Do I need to save it too?
Bercause loading the tokenizer like:
tokenizer = BertTokenizer.from\_pretrained(‘Fine\_tune\_BERT/’)
is giving error.
\>
\> OSError: Model name ‘Fine\_tune\_BERT/’ was not found in tokenizers model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese, bert-base-german-cased, bert-large-uncased-whole-word-masking, bert-large-cased-whole-word-masking, bert-large-uncased-whole-word-masking-finetuned-squad, bert-large-cased-whole-word-masking-finetuned-squad, bert-base-cased-finetuned-mrpc, bert-base-german-dbmdz-cased, bert-base-german-dbmdz-uncased, TurkuNLP/bert-base-finnish-cased-v1, TurkuNLP/bert-base-finnish-uncased-v1, wietsedv/bert-base-dutch-cased). We assumed ‘Fine\_tune\_BERT/’ was a path, a model identifier, or url to a directory containing vocabulary files named [‘vocab.txt’] but couldn’t find such vocabulary files at this path or url.
SO I assume I can load the tokenizer in the normal way?
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [October 20, 2020, 1:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-from-local%2F1651%2F2 "2020-10-20T13:48:50Z")
The model is independent from your tokenizer, so you need to also do:
```python
tokenizer.save_pretrained(’./Fine_tune_BERT/’)
```
to be able to load it back with `from_pretrained`.
---
**Author:**  [@datistiquo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdatistiquo)%5C
**Post date:** [October 20, 2020, 2:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-from-local%2F1651%2F3 "2020-10-20T14:11:16Z")
But the important issue is, do I need this? Can I still download it the normal way? Is the tokenizer affected by model fientuning? I assume no, so I could still use the tokenizer from your API?
>
---
**Author:**  [@datistiquo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdatistiquo)%5C
**Post date:** [October 20, 2020, 2:13pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-from-local%2F1651%2F4 "2020-10-20T14:13:19Z")
So:
tokenizer = BertTokenizer.from\_pretrained(‘bert-base-cased’)
but
bert\_model = TFBertModel.from\_pretrained(‘Fine\_tune\_BERT/’)
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [October 20, 2020, 2:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-from-local%2F1651%2F5 "2020-10-20T14:45:19Z")
Yes, if you didn’t do any change to the tokenizer, you can still use the pretrained version.