Special Tokens

 **\<SOS> (Start of Sequence)**: Marks the beginning of a sequence for the model to start processing.
 **\<EOS> (End of Sequence)**: Tells the model when to stop generating text or processing. 
 **\<PAD> (Padding Token)**: Pads sequences to the same length for batch processing.
 **\<UNK> (Unknown Token)**: Represents words not in the model's vocabulary.
 **\<MASK> (Mask Token)**: Used in tasks like predicting missing words in masked language models.
 **\<SEP> (Separator Token)**: Separates different segments in input, like questions from context.