| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "50256": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50257": { | |
| "content": "<BOS>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50258": { | |
| "content": "<EOS>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50259": { | |
| "content": "<PAD>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50260": { | |
| "content": "<superhero>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50261": { | |
| "content": "<action>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50262": { | |
| "content": "<drama>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50263": { | |
| "content": "<thriller>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50264": { | |
| "content": "<horror>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50265": { | |
| "content": "<sci_fi>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<superhero>", | |
| "<action>", | |
| "<drama>", | |
| "<thriller>", | |
| "<horror>", | |
| "<sci_fi>" | |
| ], | |
| "bos_token": "<BOS>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<EOS>", | |
| "errors": "replace", | |
| "model_max_length": 1024, | |
| "pad_token": "<PAD>", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "<|endoftext|>" | |
| } | |