| For training, the [ReformerModelWithLMHead] should be used as follows: | |
| python | |
| input_ids = tokenizer.encode("This is a sentence from the training data", return_tensors="pt") | |
| loss = model(input_ids, labels=input_ids)[0] | |
| Resources | |
| Text classification task guide | |
| Question answering task guide | |
| Causal language modeling task guide | |
| Masked language modeling task guide | |
| ReformerConfig | |
| [[autodoc]] ReformerConfig | |
| ReformerTokenizer | |
| [[autodoc]] ReformerTokenizer | |
| - save_vocabulary | |
| ReformerTokenizerFast | |
| [[autodoc]] ReformerTokenizerFast | |
| ReformerModel | |
| [[autodoc]] ReformerModel | |
| - forward | |
| ReformerModelWithLMHead | |
| [[autodoc]] ReformerModelWithLMHead | |
| - forward | |
| ReformerForMaskedLM | |
| [[autodoc]] ReformerForMaskedLM | |
| - forward | |
| ReformerForSequenceClassification | |
| [[autodoc]] ReformerForSequenceClassification | |
| - forward | |
| ReformerForQuestionAnswering | |
| [[autodoc]] ReformerForQuestionAnswering | |
| - forward |