Make dataset and collator for supervised fine-tuning.
(tokenizer: transformers.PreTrainedTokenizer, dataset_name, max_sample=None)
| 141 | ) |
| 142 | |
| 143 | def make_supervised_data_module(tokenizer: transformers.PreTrainedTokenizer, dataset_name, max_sample=None) -> Dict: |
| 144 | """Make dataset and collator for supervised fine-tuning.""" |
| 145 | gen_dataset = SupervisedDataset(tokenizer=tokenizer, dataset_name=dataset_name, max_sample=max_sample) |
| 146 | data_collator = DataCollatorForSupervisedDataset(tokenizer=tokenizer) |
| 147 | return gen_dataset, data_collator |
| 148 | |
| 149 | def main(args): |
| 150 | torch.manual_seed(args.seed) |
no test coverage detected