OpenCUA-7B / tokenizer_config.json
xywang626's picture
Upload folder using huggingface_hub
d1844e8 verified
{
"added_tokens_decoder": {
"151643": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "[EOS]",
"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": "<|im_user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|im_assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|reserved_token_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|reserved_token_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "[EOT]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|im_system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|reserved_token_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|reserved_token_3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|reserved_token_4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<|reserved_token_5|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151658": {
"content": "<|reserved_token_6|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151659": {
"content": "<|reserved_token_7|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151660": {
"content": "<|im_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151661": {
"content": "<|media_begin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151662": {
"content": "<|media_content|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151663": {
"content": "<|media_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151664": {
"content": "<|media_placeholder|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"152062": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"152063": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_end|>",
"<|im_user|>",
"<|im_assistant|>",
"<|reserved_token_0|>",
"<|start_header_id|>",
"<|end_header_id|>",
"<|reserved_token_1|>",
"[EOT]",
"<|im_system|>",
"<|reserved_token_2|>",
"<|reserved_token_3|>",
"<|reserved_token_4|>",
"<|reserved_token_5|>",
"<|reserved_token_6|>",
"<|reserved_token_7|>",
"<|im_middle|>",
"<|media_begin|>",
"<|media_content|>",
"<|media_end|>",
"<|media_placeholder|>"
],
"bos_token": "[BOS]",
"clean_up_tokenization_spaces": false,
"eos_token": "[EOS]",
"extra_special_tokens": {},
"chat_template": "{%- for message in messages -%}{%- if loop.first and messages[0]['role'] != 'system' -%}{{'<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>'}}{%- endif -%}{%- if message['role'] == 'system' -%}{{'<|im_system|>'}}{%- endif -%}{%- if message['role'] == 'user' -%}{{'<|im_user|>'}}{%- endif -%}{%- if message['role'] == 'assistant' -%}{{'<|im_assistant|>'}}{%- endif -%}{{- message['role'] -}}{{'<|im_middle|>'}}{%- if message['content'] is string -%}{{- message['content'] + '<|im_end|>' -}}{%- else -%}{%- for content in message['content'] -%}{%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}{{'<|media_begin|>image<|media_content|><|media_placeholder|><|media_end|>'}}{%- else -%}{{content['text']}}{%- endif -%}{%- endfor -%}{{'<|im_end|>'}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{'<|im_assistant|>assistant<|im_middle|>'}}{%- endif -%}",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"tokenizer_class": "TikTokenV3",
"unk_token": "[UNK]",
"auto_map": {
"AutoTokenizer": [
"tokenization_opencua.TikTokenV3",
null
]
}
}