Why on my local machine i am getting this error for big texts but i can run those text on hugging face inference API?
Error that i am getting:
"Token indices sequence length is longer than the specified maximum sequence length for this model (1161 > 1024). Running this sequence through the model will result in indexing errors"
So far the results i got on other texts are really accurate and great using your model, so great work guys!!
Huggingface API automatically truncates the input you give. Locally you have to pass a parameter for truncation to be true so that your inputs get truncated. (truncation=True or truncate=True)
but if i truncate wont it omit the text that maybe is important for summary and what about summary result?
after the truncation its not giving proper results , its giving uncomplete summary like incomplete sentences!!
how can i increase my out put of summary i give input of word 6000 or more but i get summary only 20-25 words why. and how to solve this.
how can i increase my out put of summary i give input of word 6000 or more but i get summary only 20-25 words why. and how to solve this.
maybe token size but you wont get bigger summary probably