tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "added_tokens_decoder": { |
| 4 | "151643": { |
| 5 | "content": "<|endoftext|>", |
| 6 | "lstrip": false, |
| 7 | "normalized": false, |
| 8 | "rstrip": false, |
| 9 | "single_word": false, |
| 10 | "special": true |
| 11 | }, |
| 12 | "151644": { |
| 13 | "content": "<|im_start|>", |
| 14 | "lstrip": false, |
| 15 | "normalized": false, |
| 16 | "rstrip": false, |
| 17 | "single_word": false, |
| 18 | "special": true |
| 19 | }, |
| 20 | "151645": { |
| 21 | "content": "<|im_end|>", |
| 22 | "lstrip": false, |
| 23 | "normalized": false, |
| 24 | "rstrip": false, |
| 25 | "single_word": false, |
| 26 | "special": true |
| 27 | }, |
| 28 | "151646": { |
| 29 | "content": "<|object_ref_start|>", |
| 30 | "lstrip": false, |
| 31 | "normalized": false, |
| 32 | "rstrip": false, |
| 33 | "single_word": false, |
| 34 | "special": true |
| 35 | }, |
| 36 | "151647": { |
| 37 | "content": "<|object_ref_end|>", |
| 38 | "lstrip": false, |
| 39 | "normalized": false, |
| 40 | "rstrip": false, |
| 41 | "single_word": false, |
| 42 | "special": true |
| 43 | }, |
| 44 | "151648": { |
| 45 | "content": "<|box_start|>", |
| 46 | "lstrip": false, |
| 47 | "normalized": false, |
| 48 | "rstrip": false, |
| 49 | "single_word": false, |
| 50 | "special": true |
| 51 | }, |
| 52 | "151649": { |
| 53 | "content": "<|box_end|>", |
| 54 | "lstrip": false, |
| 55 | "normalized": false, |
| 56 | "rstrip": false, |
| 57 | "single_word": false, |
| 58 | "special": true |
| 59 | }, |
| 60 | "151650": { |
| 61 | "content": "<|quad_start|>", |
| 62 | "lstrip": false, |
| 63 | "normalized": false, |
| 64 | "rstrip": false, |
| 65 | "single_word": false, |
| 66 | "special": true |
| 67 | }, |
| 68 | "151651": { |
| 69 | "content": "<|quad_end|>", |
| 70 | "lstrip": false, |
| 71 | "normalized": false, |
| 72 | "rstrip": false, |
| 73 | "single_word": false, |
| 74 | "special": true |
| 75 | }, |
| 76 | "151652": { |
| 77 | "content": "<|vision_start|>", |
| 78 | "lstrip": false, |
| 79 | "normalized": false, |
| 80 | "rstrip": false, |
| 81 | "single_word": false, |
| 82 | "special": true |
| 83 | }, |
| 84 | "151653": { |
| 85 | "content": "<|vision_end|>", |
| 86 | "lstrip": false, |
| 87 | "normalized": false, |
| 88 | "rstrip": false, |
| 89 | "single_word": false, |
| 90 | "special": true |
| 91 | }, |
| 92 | "151654": { |
| 93 | "content": "<|vision_pad|>", |
| 94 | "lstrip": false, |
| 95 | "normalized": false, |
| 96 | "rstrip": false, |
| 97 | "single_word": false, |
| 98 | "special": true |
| 99 | }, |
| 100 | "151655": { |
| 101 | "content": "<|image_pad|>", |
| 102 | "lstrip": false, |
| 103 | "normalized": false, |
| 104 | "rstrip": false, |
| 105 | "single_word": false, |
| 106 | "special": true |
| 107 | }, |
| 108 | "151656": { |
| 109 | "content": "<|video_pad|>", |
| 110 | "lstrip": false, |
| 111 | "normalized": false, |
| 112 | "rstrip": false, |
| 113 | "single_word": false, |
| 114 | "special": true |
| 115 | } |
| 116 | }, |
| 117 | "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|>"], |
| 118 | "bos_token": null, |
| 119 | "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 %}", |
| 120 | "clean_up_tokenization_spaces": false, |
| 121 | "eos_token": "<|im_end|>", |
| 122 | "padding_side": "left", |
| 123 | "errors": "replace", |
| 124 | "model_max_length": 32768, |
| 125 | "pad_token": "<|endoftext|>", |
| 126 | "split_special_tokens": false, |
| 127 | "tokenizer_class": "Qwen2Tokenizer", |
| 128 | "unk_token": null |
| 129 | } |
| 130 | |