390 lines
8.8 KiB
JSON
390 lines
8.8 KiB
JSON
|
{
|
||
|
"add_bos_token": false,
|
||
|
"add_eos_token": false,
|
||
|
"added_tokens_decoder": {
|
||
|
"0": {
|
||
|
"content": "<pad>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"1": {
|
||
|
"content": "<s>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"2": {
|
||
|
"content": "</s>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"3": {
|
||
|
"content": "<unk>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"50": {
|
||
|
"content": "<|im_start|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"51": {
|
||
|
"content": "<|im_end|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"52": {
|
||
|
"content": "<|object_ref_start|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"53": {
|
||
|
"content": "<|object_ref_end|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"54": {
|
||
|
"content": "<|box_start|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"55": {
|
||
|
"content": "<|box_end|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"56": {
|
||
|
"content": "<|quad_start|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"57": {
|
||
|
"content": "<|quad_end|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"58": {
|
||
|
"content": "<|vision_start|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"59": {
|
||
|
"content": "<|vision_end|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"60": {
|
||
|
"content": "<|vision_pad|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"61": {
|
||
|
"content": "<|image_pad|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"62": {
|
||
|
"content": "<|video_pad|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"63": {
|
||
|
"content": "<tool_call>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"64": {
|
||
|
"content": "</tool_call>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"65": {
|
||
|
"content": "<|fim_prefix|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"66": {
|
||
|
"content": "<|fim_middle|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"67": {
|
||
|
"content": "<|fim_suffix|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"68": {
|
||
|
"content": "<|fim_pad|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"69": {
|
||
|
"content": "<|repo_name|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"70": {
|
||
|
"content": "<|file_sep|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"71": {
|
||
|
"content": "<B_SYS>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"72": {
|
||
|
"content": "<B_USYS>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"73": {
|
||
|
"content": "<C_Q>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"74": {
|
||
|
"content": "<C_A>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"75": {
|
||
|
"content": "<B_FUNC>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"76": {
|
||
|
"content": "<B_CODE>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"77": {
|
||
|
"content": "<B_APE>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"78": {
|
||
|
"content": "<function_calling>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"79": {
|
||
|
"content": "<calc_start>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"80": {
|
||
|
"content": "<calc_end>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"81": {
|
||
|
"content": "<inner_think>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"82": {
|
||
|
"content": "<|im_sep|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"83": {
|
||
|
"content": "<|tool_call|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"84": {
|
||
|
"content": "<|arguments|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": false,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": true
|
||
|
},
|
||
|
"85": {
|
||
|
"content": "<|o1_step|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"86": {
|
||
|
"content": "<|o1_answer|>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"87": {
|
||
|
"content": "<tree_node>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
},
|
||
|
"88": {
|
||
|
"content": "</tree_node>",
|
||
|
"lstrip": false,
|
||
|
"normalized": true,
|
||
|
"rstrip": false,
|
||
|
"single_word": false,
|
||
|
"special": false
|
||
|
}
|
||
|
},
|
||
|
"additional_special_tokens": [
|
||
|
"<|im_start|>",
|
||
|
"<|im_end|>",
|
||
|
"<|object_ref_start|>",
|
||
|
"<|object_ref_end|>",
|
||
|
"<|box_start|>",
|
||
|
"<|box_end|>",
|
||
|
"<|quad_start|>",
|
||
|
"<|quad_end|>",
|
||
|
"<|vision_start|>",
|
||
|
"<|vision_end|>",
|
||
|
"<|vision_pad|>",
|
||
|
"<|image_pad|>",
|
||
|
"<|video_pad|>",
|
||
|
"<B_SYS>",
|
||
|
"<B_USYS>",
|
||
|
"<C_Q>",
|
||
|
"<C_A>",
|
||
|
"<|im_sep|>",
|
||
|
"<|tool_call|>",
|
||
|
"<|arguments|>"
|
||
|
],
|
||
|
"auto_map": {
|
||
|
"AutoTokenizer": [
|
||
|
"tokenization_baichuan.BaichuanTokenizer",
|
||
|
null
|
||
|
]
|
||
|
},
|
||
|
"bos_token": "<s>",
|
||
|
"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' %}{{'<C_Q>' + message['content']}}{% elif message['role'] == 'assistant' %}{{'<C_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 %}{{'<C_A>'}}{% endif %}",
|
||
|
"clean_up_tokenization_spaces": false,
|
||
|
"eos_token": "</s>",
|
||
|
"extra_special_tokens": {},
|
||
|
"model_max_length": 32768,
|
||
|
"pad_token": "<pad>",
|
||
|
"sp_model_kwargs": {},
|
||
|
"tokenizer_class": "BaichuanTokenizer",
|
||
|
"unk_token": "<unk>",
|
||
|
"use_fast": false
|
||
|
}
|