| { | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "50256": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50257": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50258": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50259": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|endoftext|>", | |
| "max_length": 384, | |
| "model_max_length": 1024, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "stride": 128, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "only_second", | |
| "unk_token": "<|endoftext|>" | |
| } | |