Runner#
- class FlagEmbedding.finetune.reranker.encoder_only.base.EncoderOnlyRerankerRunner(model_args: AbsRerankerModelArguments, data_args: AbsRerankerDataArguments, training_args: AbsRerankerTrainingArguments)[source]#
Encoder only reranker runner for finetuning.
- load_tokenizer_and_model() Tuple[PreTrainedTokenizer, AbsRerankerModel][source]#
Load the tokenizer and model.
- Returns:
Tokenizer and model instances.
- Return type:
Tuple[PreTrainedTokenizer, AbsEmbedderModel]
- load_trainer() EncoderOnlyRerankerTrainer[source]#
Load the trainer.
- Returns:
Loaded trainer instance.
- Return type: