33 lines
1.1 KiB
JSON
33 lines
1.1 KiB
JSON
{
|
|
"add_prefix_space": false,
|
|
"audio_bos_token": "<|audio_start|>",
|
|
"audio_eos_token": "<|audio_end|>",
|
|
"audio_token": "<|audio_pad|>",
|
|
"backend": "tokenizers",
|
|
"bos_token": null,
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"errors": "replace",
|
|
"image_token": "<|image_pad|>",
|
|
"is_local": false,
|
|
"local_files_only": false,
|
|
"model_max_length": 262144,
|
|
"model_specific_special_tokens": {
|
|
"audio_bos_token": "<|audio_start|>",
|
|
"audio_eos_token": "<|audio_end|>",
|
|
"audio_token": "<|audio_pad|>",
|
|
"image_token": "<|image_pad|>",
|
|
"video_token": "<|video_pad|>",
|
|
"vision_bos_token": "<|vision_start|>",
|
|
"vision_eos_token": "<|vision_end|>"
|
|
},
|
|
"pad_token": "<|endoftext|>",
|
|
"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+",
|
|
"split_special_tokens": false,
|
|
"tokenizer_class": "Qwen2Tokenizer",
|
|
"unk_token": null,
|
|
"video_token": "<|video_pad|>",
|
|
"vision_bos_token": "<|vision_start|>",
|
|
"vision_eos_token": "<|vision_end|>"
|
|
}
|