Runner#

class FlagEmbedding.finetune.embedder.encoder_only.base.EncoderOnlyEmbedderRunner(model_args: AbsEmbedderModelArguments, data_args: AbsEmbedderDataArguments, training_args: AbsEmbedderTrainingArguments)[source]#

Finetune Runner for base embedding models.

load_tokenizer_and_model() → Tuple[PreTrainedTokenizer, AbsEmbedderModel][source]#

Load tokenizer and model.

Returns:

Tokenizer and model instances.

Return type:

Tuple[PreTrainedTokenizer, AbsEmbedderModel]

load_trainer() → EncoderOnlyEmbedderTrainer[source]#

Load the trainer.

Returns:

Loaded trainer instance.

Return type:

EncoderOnlyEmbedderTrainer