| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "<|endoftext|>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Digits", | |
| "individual_digits": true | |
| }, | |
| "post_processor": { | |
| "type": "ByteLevel", | |
| "add_prefix_space": true, | |
| "trim_offsets": false, | |
| "use_regex": true | |
| }, | |
| "decoder": { | |
| "type": "ByteLevel", | |
| "add_prefix_space": true, | |
| "trim_offsets": true, | |
| "use_regex": true | |
| }, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": null, | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": false, | |
| "byte_fallback": false, | |
| "vocab": { | |
| "<|endoftext|>": 0, | |
| "$": 1, | |
| "+": 2, | |
| ",": 3, | |
| "0": 4, | |
| "1": 5, | |
| "2": 6, | |
| "3": 7, | |
| "4": 8, | |
| "5": 9, | |
| "6": 10, | |
| "7": 11, | |
| "8": 12, | |
| "9": 13, | |
| ";": 14, | |
| "=": 15 | |
| }, | |
| "merges": [] | |
| } | |
| } |