| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<unk>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "<s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 2, |
| "content": "</s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<pad>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "Metaspace", |
| "replacement": "▁", |
| "prepend_scheme": "always", |
| "split": 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": "Sequence", |
| "decoders": [ |
| { |
| "type": "Replace", |
| "pattern": { |
| "String": "▁" |
| }, |
| "content": " " |
| }, |
| { |
| "type": "ByteFallback" |
| }, |
| { |
| "type": "Fuse" |
| }, |
| { |
| "type": "Strip", |
| "content": " ", |
| "start": 1, |
| "stop": 0 |
| } |
| ] |
| }, |
| "model": { |
| "type": "BPE", |
| "dropout": null, |
| "unk_token": null, |
| "continuing_subword_prefix": null, |
| "end_of_word_suffix": null, |
| "fuse_unk": true, |
| "byte_fallback": true, |
| "ignore_merges": false, |
| "vocab": { |
| "<unk>": 0, |
| "<s>": 1, |
| "</s>": 2 |
| }, |
| "merges": [] |
| } |
| } |
