(self, prompt: str, stop: Optional[List[str]] = None)
| 37 | return self.model_name |
| 38 | |
| 39 | def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str: |
| 40 | inputs = self.tokenizer( |
| 41 | prompt, |
| 42 | padding=True, |
| 43 | max_length=self.tokenizer.model_max_length, |
| 44 | truncation=True, |
| 45 | return_tensors="pt" |
| 46 | ) |
| 47 | inputs_len = inputs["input_ids"].shape[1] |
| 48 | generated_outputs = self.model.generate( |
| 49 | input_ids=(inputs["input_ids"].cuda() if self.use_gpu else inputs["input_ids"]), |
| 50 | attention_mask=(inputs["attention_mask"].cuda() if self.use_gpu else inputs["attention_mask"]), |
| 51 | max_new_tokens=512, |
| 52 | eos_token_id=self.tokenizer.eos_token_id, |
| 53 | bos_token_id=self.tokenizer.bos_token_id, |
| 54 | pad_token_id=self.tokenizer.pad_token_id, |
| 55 | ) |
| 56 | decoded_output = self.tokenizer.batch_decode( |
| 57 | generated_outputs[..., inputs_len:], skip_special_tokens=True) |
| 58 | output = decoded_output[0] |
| 59 | return output |
| 60 | |
| 61 | @property |
| 62 | def _identifying_params(self) -> Mapping[str, Any]: |
nothing calls this directly
no outgoing calls
no test coverage detected