| { | |
| "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": { | |
| "type": "NFC" | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Sequence", | |
| "pretokenizers": [ | |
| { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| { | |
| "type": "ByteLevel", | |
| "add_prefix_space": false, | |
| "trim_offsets": true, | |
| "use_regex": false | |
| } | |
| ] | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": {} | |
| }, | |
| "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": { | |
| "<|endoftext|>": 0 | |
| }, | |
| "merges": [] | |
| } | |
| } |