r""" Dataset attributes.

r""" A callback for saving the processor.

r""" General class for chat models. Backed by huggingface or vllm engines. Supports both sync and async methods. Sync methods: chat(), st

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

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

r""" Data collator for pairwise data.

r""" Computes reward accuracy and supports `batch_eval_metrics`.

r""" Computes accuracy and supports `batch_eval_metrics`.

r""" Computes text similarity scores and supports `batch_eval_metrics`. Wraps the tokenizer into metric functions, used in CustomSeq2SeqTrain

r""" Inherits PPOTrainer.

r""" Inherits Seq2SeqTrainer to compute generative metrics such as BLEU and ROUGE.

r""" Inherits Trainer for custom optimizer.

r""" A dummy optimizer used for the GaLore algorithm.

r""" Data collator for KTO data.

r""" A callback for logging training and evaluation status.

r""" Redirects the logging output to the logging file for LLaMA Board.

r""" Data collator that supports VLMs. Features should contain input_ids, attention_mask, labels and images.

r""" Inherits Trainer to compute pairwise loss.

r""" Data collator for 4d attention mask.

r""" Arguments pertaining to the BAdam optimizer.

r""" Base class for inference engine of chat models. Must implements async methods: chat(), stream_chat() and get_scores().

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

r""" Arguments pertaining to the Distillation.

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

r""" Arguments pertaining to the model export.

r""" A callback for fixing the checkpoint for valuehead models.

r""" Arguments pertaining to the freeze (partial-parameter) training.