Hi there,
Can someone tell me whether I shall learn about text preprocessing before starting this course?
Additionally, are the traditional text preprocessing methods similar to the ones used today. Before I learn to build an LLM model is it important to know Stemming, Lemmatization etc… from NLTK?
Have the methods to tokenize etc, have changed or are we still using NLTK before using LLAMA?
I greatly appreciate any response and help regarding this!
Thank you!