| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "50257": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50258": { | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50259": { | |
| "content": "<|unknown|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "do_lower_case": false, | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "full_tokenizer_file": null, | |
| "max_len": 1024, | |
| "model_max_length": 1024, | |
| "pad_token": null, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "<unk>" | |
| } | |