Update tokenizer_config.json
Browse files- tokenizer_config.json +69 -20
tokenizer_config.json
CHANGED
@@ -1,3 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
@@ -114,31 +178,16 @@
|
|
114 |
"special": true
|
115 |
}
|
116 |
},
|
117 |
-
"additional_special_tokens": [
|
118 |
-
"<|im_start|>",
|
119 |
-
"<|im_end|>",
|
120 |
-
"<|object_ref_start|>",
|
121 |
-
"<|object_ref_end|>",
|
122 |
-
"<|box_start|>",
|
123 |
-
"<|box_end|>",
|
124 |
-
"<|quad_start|>",
|
125 |
-
"<|quad_end|>",
|
126 |
-
"<|vision_start|>",
|
127 |
-
"<|vision_end|>",
|
128 |
-
"<|vision_pad|>",
|
129 |
-
"<|image_pad|>",
|
130 |
-
"<|video_pad|>"
|
131 |
-
],
|
132 |
"bos_token": null,
|
133 |
"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 %}",
|
134 |
"clean_up_tokenization_spaces": false,
|
135 |
"eos_token": "<|im_end|>",
|
|
|
136 |
"errors": "replace",
|
137 |
-
"model_max_length":
|
138 |
-
"pad_token":
|
139 |
-
"padding_side": "right",
|
140 |
-
"processor_class": "Qwen2VLProcessor",
|
141 |
"split_special_tokens": false,
|
142 |
"tokenizer_class": "Qwen2Tokenizer",
|
143 |
"unk_token": null
|
144 |
-
}
|
|
|
1 |
+
Hugging Face's logo
|
2 |
+
Hugging Face
|
3 |
+
Models
|
4 |
+
Datasets
|
5 |
+
Spaces
|
6 |
+
Posts
|
7 |
+
Docs
|
8 |
+
Enterprise
|
9 |
+
Pricing
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
|
14 |
+
Qwen
|
15 |
+
/
|
16 |
+
Qwen2-VL-2B-Instruct
|
17 |
+
|
18 |
+
like
|
19 |
+
378
|
20 |
+
|
21 |
+
Follow
|
22 |
+
|
23 |
+
Qwen
|
24 |
+
10.6k
|
25 |
+
Image-Text-to-Text
|
26 |
+
Transformers
|
27 |
+
Safetensors
|
28 |
+
English
|
29 |
+
qwen2_vl
|
30 |
+
multimodal
|
31 |
+
conversational
|
32 |
+
text-generation-inference
|
33 |
+
Inference Endpoints
|
34 |
+
|
35 |
+
arxiv:
|
36 |
+
2409.12191
|
37 |
+
|
38 |
+
arxiv:
|
39 |
+
2308.12966
|
40 |
+
|
41 |
+
License:
|
42 |
+
apache-2.0
|
43 |
+
Model card
|
44 |
+
Files and versions
|
45 |
+
Community
|
46 |
+
23
|
47 |
+
Qwen2-VL-2B-Instruct
|
48 |
+
/
|
49 |
+
tokenizer_config.json
|
50 |
+
|
51 |
+
yangapku's picture
|
52 |
+
yangapku
|
53 |
+
Initial commit
|
54 |
+
e28f5d3
|
55 |
+
5 months ago
|
56 |
+
raw
|
57 |
+
|
58 |
+
Copy download link
|
59 |
+
history
|
60 |
+
blame
|
61 |
+
contribute
|
62 |
+
delete
|
63 |
+
|
64 |
+
4.19 kB
|
65 |
{
|
66 |
"add_prefix_space": false,
|
67 |
"added_tokens_decoder": {
|
|
|
178 |
"special": true
|
179 |
}
|
180 |
},
|
181 |
+
"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|>"],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
182 |
"bos_token": null,
|
183 |
"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 %}",
|
184 |
"clean_up_tokenization_spaces": false,
|
185 |
"eos_token": "<|im_end|>",
|
186 |
+
"padding_side": "left",
|
187 |
"errors": "replace",
|
188 |
+
"model_max_length": 32768,
|
189 |
+
"pad_token": "<|endoftext|>",
|
|
|
|
|
190 |
"split_special_tokens": false,
|
191 |
"tokenizer_class": "Qwen2Tokenizer",
|
192 |
"unk_token": null
|
193 |
+
}
|