{ "version": "1.0", "truncation": null, "padding": { "strategy": "BatchLongest", "direction": "Left", "pad_to_multiple_of": null, "pad_id": 0, "pad_type_id": 0, "pad_token": "" }, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "|||." }, "behavior": "Isolated", "invert": false }, "post_processor": null, "decoder": null, "model": { "type": "WordLevel", "vocab": { "": 0, "": 1, "": 2, "": 3, "": 4, "": 5, ".": 6, "(": 7, ")": 8, "A": 9, "C": 10, "G": 11, "U": 12 }, "unk_token": "" } }