numind/NuExtract3
36461k
1{2 "add_prefix_space": false,3 "audio_bos_token": "<|audio_start|>",4 "audio_eos_token": "<|audio_end|>",5 "audio_token": "<|audio_pad|>",6 "backend": "tokenizers",7 "bos_token": null,8 "clean_up_tokenization_spaces": false,9 "eos_token": "<|im_end|>",10 "errors": "replace",11 "image_token": "<|image_pad|>",12 "is_local": false,13 "local_files_only": false,14 "model_max_length": 262144,15 "model_specific_special_tokens": {16 "audio_bos_token": "<|audio_start|>",17 "audio_eos_token": "<|audio_end|>",18 "audio_token": "<|audio_pad|>",19 "image_token": "<|image_pad|>",20 "video_token": "<|video_pad|>",21 "vision_bos_token": "<|vision_start|>",22 "vision_eos_token": "<|vision_end|>"23 },24 "pad_token": "<|endoftext|>",25 "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",26 "processor_class": "Qwen3VLProcessor",27 "split_special_tokens": false,28 "tokenizer_class": "TokenizersBackend",29 "unk_token": null,30 "video_token": "<|video_pad|>",31 "vision_bos_token": "<|vision_start|>",32 "vision_eos_token": "<|vision_end|>"33}34 