{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<|beginoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true }, { "id": 1, "content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "<|unknown|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "NFC" }, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true }, "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": false, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "<|unknown|>", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "<|beginoftext|>": 0, "<|padding|>": 1, "<|unknown|>": 2, "a": 3, "c": 4, "g": 5, "t": 6, "n": 7 }, "merges": [] } }