VideoLLaMA3-2B-Image / tokenizer_config.json
ClownRat's picture
Upload processor
0c5b101 verified
raw
history blame
7.5 kB
{
"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": "<image>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151666": {
"content": "<|stream_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151667": {
"content": "<|stream_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"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|>"
],
"auto_map": {
"AutoProcessor": "processing_videollama3.Videollama3Qwen2Processor"
},
"bos_token": null,
"chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if add_system_prompt and loop.first and message['role'] != 'system' %}\n {{- '<|im_start|>system\nYou are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>\n' -}}\n {% endif %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content is string %}\n {{- content -}}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% elif content['type'] == 'image' or 'image' in content %}\n {% if 'timestamp' in content %}\n {{- 'Time ' + content['timestamp'] | round(1) | string + 's: ' -}}\n {% endif %}\n {{- image_token + '\n' -}}\n {% elif content['type'] == 'video' or 'video' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n {{- image_token + ',' -}}\n {% else %}\n {{- image_token + '\n' -}}\n {% endif %}\n {% endfor %}\n {% endif %}\n {% endfor %}\n {% if identifier == 'stream' %}\n {{- '<|' + identifier + '_end|>' -}}\n {% else %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"processor_class": "Videollama3Qwen2Processor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}