File size: 520 Bytes
28118c7 64d55e2 28118c7 64d55e2 28118c7 64d55e2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | """
Training utilities for domainTokenizer.
- data_pipeline: tokenize_user_sequences, pack_sequences, prepare_clm_dataset
- pretrain: pretrain_domain_model
- finetune_data: DomainFinetuneDataset, prepare_finetune_dataset
- finetune: finetune_domain_model
"""
from .data_pipeline import tokenize_user_sequences, pack_sequences, prepare_clm_dataset
from .pretrain import pretrain_domain_model
from .finetune_data import DomainFinetuneDataset, prepare_finetune_dataset
from .finetune import finetune_domain_model
|