{ "version": "1.0", "truncation": null, "padding": null, "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": "<|vision_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "<|vision_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 6, "content": "<|image_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 7, "content": "<|video_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Whitespace" }, "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": null, "model": { "type": "WordLevel", "vocab": { "": 0, "": 1, "": 2, "": 3, "<|vision_start|>": 4, "<|vision_end|>": 5, "<|image_pad|>": 6, "<|video_pad|>": 7, "lower": 8, "newer": 9, "upper": 10, "older": 11, "longer": 12, "string": 13, "Describe": 14, "this": 15, "user": 16, "assistant": 17 }, "unk_token": "" } }