209 lines
5.5 KiB
JSON
209 lines
5.5 KiB
JSON
|
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"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": "<|object_ref_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151647": {
|
||
|
|
"content": "<|object_ref_end|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151648": {
|
||
|
|
"content": "<|box_start|>",
|
||
|
|
"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_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151653": {
|
||
|
|
"content": "<|vision_end|>",
|
||
|
|
"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_pad|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151656": {
|
||
|
|
"content": "<|video_pad|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"151657": {
|
||
|
|
"content": "<tool_call>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"151658": {
|
||
|
|
"content": "</tool_call>",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"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|>"
|
||
|
|
],
|
||
|
|
"bos_token": null,
|
||
|
|
"chat_template": "{{ bos_token }}A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>. {% for message in messages %}{% if message['role'] == 'user' %}User: You must put your answer inside <answer> </answer> tags, i.e., <answer> answer here </answer>. And your final answer will be extracted automatically by the \\boxed{} tag.\nThis is the problem:\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}Assistant: <think>{{ message['content'] }}</answer>\n{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant: <think>{% endif %}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 131072,
|
||
|
|
"pad_token": "<|endoftext|>",
|
||
|
|
"split_special_tokens": false,
|
||
|
|
"tokenizer_class": "Qwen2Tokenizer",
|
||
|
|
"unk_token": null
|
||
|
|
}
|