AITQE / tokenizer_config.json
HymanH's picture
init commit
4489d10 verified
{
"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": "<B_SYS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<B_USYS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<C_Q>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<C_A>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<B_FUNC>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<B_CODE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<B_APE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"151653": {
"content": "<function_calling>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"151654": {
"content": "<calc_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"151655": {
"content": "<calc_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"151656": {
"content": "<inner_think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"151657": {
"content": "<audio_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151658": {
"content": "<audio_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151659": {
"content": "<audio_pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151660": {
"content": "<img_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151661": {
"content": "<img_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151662": {
"content": "<img_pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151663": {
"content": "<img_newline>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151664": {
"content": "<box_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151665": {
"content": "<box_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151666": {
"content": "<box_delim>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151667": {
"content": "<ref_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151668": {
"content": "<ref_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151669": {
"content": "<img_delim>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151670": {
"content": "<polygon_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151671": {
"content": "<polygon_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151672": {
"content": "<pad_token>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151673": {
"content": "<reserved_113>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151674": {
"content": "<reserved_114>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151675": {
"content": "<reserved_115>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151676": {
"content": "<score_caption>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151677": {
"content": "</score_caption>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151678": {
"content": "<Overall>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<B_SYS>",
"<B_USYS>",
"<C_Q>",
"<C_A>",
"<B_FUNC>",
"<B_CODE>",
"<B_APE>",
"<function_calling>",
"<calc_start>",
"<calc_end>",
"<inner_think>",
"<audio_start>",
"<audio_end>",
"<audio_pad>",
"<img_start>",
"<img_end>",
"<img_pad>",
"<img_newline>",
"<box_start>",
"<box_end>",
"<box_delim>",
"<ref_start>",
"<ref_end>",
"<img_delim>",
"<polygon_start>",
"<polygon_end>",
"<pad_token>",
"<reserved_113>",
"<reserved_114>",
"<reserved_115>",
"<score_caption>",
"</score_caption>",
"<Overall>"
],
"bos_token": null,
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<B_SYS>' + message['content']}}{% elif message['role'] == 'user_system' %}{{'<B_USYS>' + message['content']}}{% elif message['role'] == 'user' %}{{'<H_Q>' + message['content']}}{% elif message['role'] == 'assistant' %}{{'<H_A>' + message['content']}}{% elif message['role'] == 'function' %}{{'<B_FUNC>' + message['content']}}{% elif message['role'] == 'code' %}{{'<B_CODE>' + message['content']}}{% else %}{{ raise_exception('Invalid message role: ' + message['role']) }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'<H_A>'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<pad_token>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}