Some warning appears when the model outputs the answer. How can I deal with it?
The attention mask and the pad token id were not set yet. As a consequence, you may observe unexpected behavior. Please pass your input's 'attention_mask' to obtain reliable results. Setting 'pad_token_id' to 'eos_token_id':2 for open-end generation.
Some warning appears when the model outputs the answer. How can I deal with it?
The attention mask and the pad token id were not set yet. As a consequence, you may observe unexpected behavior. Please pass your input's 'attention_mask' to obtain reliable results. Setting 'pad_token_id' to 'eos_token_id':2 for open-end generation.