| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "bos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "errors": "replace", | |
| "model_max_length": 2048, | |
| "pad_token": { | |
| "__type": "AddedToken", | |
| "content": "<|pad|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |