(self, data, tokenizer, tokenize)
| 406 | PATH = '/dataset/fd5061f6/english_data/wikibook' |
| 407 | |
| 408 | def process_line(self, data, tokenizer, tokenize): |
| 409 | if data: |
| 410 | prompt, text = "", data |
| 411 | prompt, text = self.process_sample(prompt, tokenizer, tokenize), self.process_sample(text, tokenizer, |
| 412 | tokenize) |
| 413 | return [prompt], [text] |
| 414 | else: |
| 415 | return [], [] |
| 416 | |
| 417 | |
| 418 | class Pile(PromptReader): |
nothing calls this directly
no test coverage detected