{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<|pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<|begin_of_text|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "<|end_of_text|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "<|eot_id|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 6, "content": "<|start_header_id|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 7, "content": "<|end_header_id|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Prepend", "prepend": "▁" }, { "type": "Replace", "pattern": { "String": " " }, "content": "▁" } ] }, "pre_tokenizer": null, "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": { "<|pad|>": 0, "<|begin_of_text|>": 1, "<|end_of_text|>": 2, "\t": 3, "▁▁": 4, "<|eot_id|>": 5, "<|start_header_id|>": 6, "<|end_header_id|>": 7, "\n": 8, "
": 21, "
": 22, "": 23, "