r""" Computes and stores the average and current value.

An entity identified in some text.

r""" Wraps the tokenizer into metric functions, used in Seq2SeqPeftTrainer.

r""" Inherits PPOTrainer.

r""" Inherits PeftTrainer to compute generative metrics such as BLEU and ROUGE.

r""" Data collator for pairwise data.

A date. It returns a different sparql name from a value or normal entity.

r""" Arguments pertaining to which techniques we are going to fine-tuning with.

r""" Arguments pertaining to specify the decoding parameters.

r""" Data collator for pairwise data.

r""" Inherits PeftTrainer to compute pairwise loss.

r""" Arguments pertaining to what data we are going to input our model for training and evaluation.

An entity. There are different types of entities inheriting from this class, e.g., knowledge base entities and values.

A memory based index for finding entities. Remember to delete the old _mid_vocab and _surface_index if updated the file (or choose a different pre

r""" Arguments pertaining to which stage we are going to perform.

A KB entity.

r""" Arguments pertaining to which model/config/tokenizer we are going to fine-tune.

A value. Also has a name identical to its value.