PPDocBee-7B-1210 / tokenizer_config.json
luyao-mix's picture
upload PPDocBee-7B-1210 weight
bb0531f verified
{"errors": "replace", "unk_token": null, "bos_token": null, "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "clean_up_tokenization_spaces": false, "split_special_tokens": false, "add_prefix_space": false, "added_tokens_decoder": {"151643": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151644": {"content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151645": {"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151646": {"content": "<|object_ref_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151647": {"content": "<|object_ref_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151648": {"content": "<|box_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151649": {"content": "<|box_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151650": {"content": "<|quad_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151651": {"content": "<|quad_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151652": {"content": "<|vision_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151653": {"content": "<|vision_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151654": {"content": "<|vision_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151655": {"content": "<|image_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151656": {"content": "<|video_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": 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|>"], "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}", "padding_side": "left", "model_max_length": 32768, "tokenizer_class": "Qwen2Tokenizer", "added_tokens_file": null, "special_tokens_map_file": null, "chat_template_file": null}