# Num\_labels creates an error for some models
**URL:**
**Author:**  [@olaffson](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Folaffson)%5C
**Post date:** [August 3, 2021, 1:10pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fnum-labels-creates-an-error-for-some-models%2F8937%2F1 "2021-08-03T13:10:09Z")
Hello,
I am training a classifier for three classes `(bad, medium, good)` using `distilbert-base-uncased-finetuned-sst-2-english` but after saving the model to disk and re-loading it I am getting a strange error
```auto
from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
model = TFAutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
tokenizer.save_pretrained('finetuned')
model.save_pretrained('finetuned')
model.from_pretrained('finetuned', num_labels = 3)
ValueError: cannot reshape array of size 1536 into shape (768,3)
```
This approach worked with `bert-base-uncased`. Am I doing something wrong here?
Thanks!
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 4:08pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fnum-labels-creates-an-error-for-some-models%2F8937%2F2 "2021-08-03T16:08:33Z")
With the latest version installed, you need to add `ignore_mismatched_sizes=True` to your `from_pretrained` call for this to work.
Otherwise, you try to load a model with 2 labels inside a model with 3 labels, and you get mismatched sizes like that.
---
**Author:**  [@olaffson](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Folaffson)%5C
**Post date:** [August 3, 2021, 4:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fnum-labels-creates-an-error-for-some-models%2F8937%2F3 "2021-08-03T16:12:29Z")
thanks @sgugger, life saving tip! 🙏