fix: strictly cap max_seq_length and model_max_length to 8192 for RoBERTa position embeddings
0f0286c verified | { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "<mask>", | |
| "max_length": 8192, | |
| "model_max_length": 8192, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<pad>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "</s>", | |
| "stride": 0, | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } |