| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<|pad|>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "<|unk|>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 2, |
| "content": "<|startoftext|>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<|endoftext|>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "ByteLevel", |
| "add_prefix_space": false, |
| "trim_offsets": true, |
| "use_regex": 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": "", |
| "end_of_word_suffix": "", |
| "fuse_unk": false, |
| "byte_fallback": false, |
| "ignore_merges": false, |
| "vocab": { |
| "<|pad|>": 0, |
| "<|unk|>": 1, |
| "<|startoftext|>": 2, |
| "<|endoftext|>": 3, |
| "<|mask|>": 4, |
| "A": 5, |
| "C": 6, |
| "D": 7, |
| "E": 8, |
| "F": 9, |
| "G": 10, |
| "H": 11, |
| "I": 12, |
| "K": 13, |
| "L": 14, |
| "M": 15, |
| "N": 16, |
| "P": 17, |
| "Q": 18, |
| "R": 19, |
| "S": 20, |
| "T": 21, |
| "V": 22, |
| "W": 23, |
| "Y": 24 |
| }, |
| "merges": [] |
| } |
| } |
