Hello there!
Sorry for the simple question, but consider the example below
import pandas as pd
import numpy as np
data = pd.DataFrame({'text' : ['this is good!', 'amazing stuff',
'not good at all', 'not very nice'],
'label': [1,1,0,0]})
data
Out[3]:
text label
0 this is good! 1
1 amazing stuff 1
2 not good at all 0
3 not very nice 0
As you can see, I have a small dataset containing text and label (positive vs. negative).
I would like to understand to to train a BERT/ DistilBERT model for text classification using Huggingface and tensorflow. Is there a simple way to proceed? Can you share a minimal working example here?
Thanks!