242 lines
6.3 KiB
JSON
242 lines
6.3 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
|
||
},
|
||
"151665": {
|
||
"content": "<tool_response>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": false
|
||
},
|
||
"151666": {
|
||
"content": "</tool_response>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": false
|
||
},
|
||
"151667": {
|
||
"content": "<think>",
|
||
"lstrip": false,
|
||
"normalized": false,
|
||
"rstrip": false,
|
||
"single_word": false,
|
||
"special": false
|
||
},
|
||
"151668": {
|
||
"content": "</think>",
|
||
"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": "{% set default_system = '你是磐石-科学基础大模型（S1-Base），是由中国科学院 ScienceOne 团队训练的人工智能助手。训练数据来自中国科学院文献情报中心积累的大规模高质量数据集，以及 ScienceOne 团队构建的高质量学科数据，覆盖数学、物理、化学、天文、地理、生物等学科。' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = default_system + '\n\n' + messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = default_system %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\n' }}{% endif %}{% endfor %}",
|
||
"clean_up_tokenization_spaces": false,
|
||
"eos_token": "<|im_end|>",
|
||
"errors": "replace",
|
||
"extra_special_tokens": {},
|
||
"model_max_length": 131072,
|
||
"pad_token": "<|endoftext|>",
|
||
"padding_side": "right",
|
||
"split_special_tokens": false,
|
||
"tokenizer_class": "Qwen2Tokenizer",
|
||
"unk_token": null
|
||
}
|