{ "add_prefix_space": false, "added_tokens_decoder": { "151643": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151644": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151645": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151646": { "content": "<|AUDIO|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151647": { "content": "<|audio_bos|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151648": { "content": "<|audio_eos|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151649": { "content": "<|box_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151650": { "content": "<|quad_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151651": { "content": "<|quad_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151652": { "content": "<|vision_bos|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151653": { "content": "<|vision_eos|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151654": { "content": "<|vision_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151655": { "content": "<|IMAGE|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151656": { "content": "<|VIDEO|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151657": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151658": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151659": { "content": "<|fim_prefix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151660": { "content": "<|fim_middle|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151661": { "content": "<|fim_suffix|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151662": { "content": "<|fim_pad|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151663": { "content": "<|repo_name|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151664": { "content": "<|file_sep|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false }, "151665": { "content": "<|en|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151666": { "content": "<|kr|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151667": { "content": "<|de|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151668": { "content": "<|es|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151669": { "content": "<|fr|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151670": { "content": "<|hi|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151671": { "content": "<|uk|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151672": { "content": "<|th|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151673": { "content": "<|vi|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151674": { "content": "<|nl|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151675": { "content": "<|pt|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151676": { "content": "<|id|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151677": { "content": "<|ru|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151678": { "content": "<|it|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151679": { "content": "<|ar|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151680": { "content": "<|jp|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "151681": { "content": "<|unknown|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [ "<|en|>", "<|kr|>", "<|de|>", "<|es|>", "<|fr|>", "<|hi|>", "<|uk|>", "<|th|>", "<|vi|>", "<|nl|>", "<|pt|>", "<|id|>", "<|ru|>", "<|it|>", "<|ar|>", "<|jp|>", "<|unknown|>" ], "audio_bos_token": "<|audio_bos|>", "audio_eos_token": "<|audio_eos|>", "audio_token": "<|AUDIO|>", "auto_map": { "AutoProcessor": "processing_midashenglm.MiDashengLMProcessor" }, "bos_token": null, "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", "extra_special_tokens": { "audio_bos_token": "<|audio_bos|>", "audio_eos_token": "<|audio_eos|>", "audio_token": "<|AUDIO|>", "image_token": "<|IMAGE|>", "video_token": "<|VIDEO|>", "vision_bos_token": "<|vision_bos|>", "vision_eos_token": "<|vision_eos|>" }, "image_token": "<|IMAGE|>", "model_max_length": 32768, "pad_token": "<|endoftext|>", "processor_class": "MiDashengLMProcessor", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null, "video_token": "<|VIDEO|>", "vision_bos_token": "<|vision_bos|>", "vision_eos_token": "<|vision_eos|>" }