# Unable to apply transfer learning to certain models **URL:** \ **Category:** Intermediate\ **Created:** [March 23, 2021, 5:00pm UTC](https://discuss.huggingface.co/t/unable-to-apply-transfer-learning-to-certain-models/5002 "2021-03-23T17:00:12Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![MarkyMark](https://avatars.discourse-cdn.com/v4/letter/m/958977/32.png) [@MarkyMark](https://discuss.huggingface.co/u/MarkyMark)\ **Post date:** [March 23, 2021, 5:00pm UTC](https://discuss.huggingface.co/t/unable-to-apply-transfer-learning-to-certain-models/5002/1 "2021-03-23T17:00:12Z")
Hello Huggingface community - As a researcher into NLP I am impressed with Huggingface. I am looking currently at sentiment analysis of tweets. I began with a Bert-base-cased model, and fine-tuned it with a 5000 tweet labelled data-set to recognise sentiment as either positive negative or neutral. However, when I tried to fine-tune 'NLPtown’s BERT cased sentiemnt model instead - I received the following error… ## Epoch 1 / 20 ValueError Traceback (most recent call last) in () 18 19 #train model —\> 20 train\_loss, \_ = train() 21 22 #evaluate model * * * 2 frames * * * in forward(self, sent\_id, mask) 33 34 #pass the inputs to the model —\> 35 \_, cls\_hs = self.bert(sent\_id, attention\_mask=mask) 36 37 #print(“Output width of this transformer is”,cls\_hs.shape[1]) ValueError: not enough values to unpack (expected 2, got 1) The Python code which worked seamlessly previously on a base BERT model now no longer functions. I will appreciate some steerage please on this issue and am happy to provide more details as necessary. For the moment I shall simply stste that code is Python 3.8 running on a Windows 10 laptop within a COLAB - thanks in advance! Mark