Hugging Face's logo

llmware
/
qwen2-vl-2b-instruct-ov

OpenVINO
qwen2_vl
green
llmware-vision
p2
ov
emerald
Model card Files Community
doberst commited on
Commit
125bac3
•
1 Parent(s): ebe492f

Upload 15 files

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. chat_template.json +3 -0
  4. config.json +48 -0
  5. merges.txt +0 -0
  6. openvino_language_model.xml +0 -0
  7. openvino_text_embeddings_model.xml +107 -0
  8. openvino_vision_embeddings_merger_model.bin +3 -0
  9. openvino_vision_embeddings_merger_model.xml +0 -0
  10. openvino_vision_embeddings_model.bin +3 -0
  11. openvino_vision_embeddings_model.xml +167 -0
  12. preprocessor_config.json +29 -0
  13. special_tokens_map.json +31 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +144 -0
  16. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "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 %}"
3
+ }
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\darre\\Downloads\\Qwen2-VL-2B-Instruct",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 2,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.45.2",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "hidden_size": 1536,
40
+ "in_chans": 3,
41
+ "model_type": "qwen2_vl",
42
+ "spatial_patch_size": 14
43
+ },
44
+ "vision_end_token_id": 151653,
45
+ "vision_start_token_id": 151652,
46
+ "vision_token_id": 151654,
47
+ "vocab_size": 151936
48
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_language_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model0" version="11">
3
+ <layers>
4
+ <layer id="0" name="input" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="input">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="self.weight_compressed" type="Const" version="opset1">
14
+ <data element_type="f16" shape="151936, 1536" offset="0" size="466747392" />
15
+ <output>
16
+ <port id="0" precision="FP16" names="self.weight">
17
+ <dim>151936</dim>
18
+ <dim>1536</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="self.weight" type="Convert" version="opset1">
23
+ <data destination_type="f32" />
24
+ <rt_info>
25
+ <attribute name="decompression" version="0" />
26
+ </rt_info>
27
+ <input>
28
+ <port id="0" precision="FP16">
29
+ <dim>151936</dim>
30
+ <dim>1536</dim>
31
+ </port>
32
+ </input>
33
+ <output>
34
+ <port id="1" precision="FP32">
35
+ <dim>151936</dim>
36
+ <dim>1536</dim>
37
+ </port>
38
+ </output>
39
+ </layer>
40
+ <layer id="3" name="aten::embedding/Convert" type="Convert" version="opset1">
41
+ <data destination_type="i32" />
42
+ <input>
43
+ <port id="0" precision="I64">
44
+ <dim>-1</dim>
45
+ <dim>-1</dim>
46
+ </port>
47
+ </input>
48
+ <output>
49
+ <port id="1" precision="I32">
50
+ <dim>-1</dim>
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="aten::embedding/Constant" type="Const" version="opset1">
56
+ <data element_type="i32" shape="" offset="466747392" size="4" />
57
+ <output>
58
+ <port id="0" precision="I32" />
59
+ </output>
60
+ </layer>
61
+ <layer id="5" name="aten::embedding/Gather" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="FP32">
65
+ <dim>151936</dim>
66
+ <dim>1536</dim>
67
+ </port>
68
+ <port id="1" precision="I32">
69
+ <dim>-1</dim>
70
+ <dim>-1</dim>
71
+ </port>
72
+ <port id="2" precision="I32" />
73
+ </input>
74
+ <output>
75
+ <port id="3" precision="FP32">
76
+ <dim>-1</dim>
77
+ <dim>-1</dim>
78
+ <dim>1536</dim>
79
+ </port>
80
+ </output>
81
+ </layer>
82
+ <layer id="6" name="Result_11" type="Result" version="opset1">
83
+ <input>
84
+ <port id="0" precision="FP32">
85
+ <dim>-1</dim>
86
+ <dim>-1</dim>
87
+ <dim>1536</dim>
88
+ </port>
89
+ </input>
90
+ </layer>
91
+ </layers>
92
+ <edges>
93
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
94
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
95
+ <edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
96
+ <edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
97
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
98
+ <edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
99
+ </edges>
100
+ <rt_info>
101
+ <Runtime_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
102
+ <conversion_parameters>
103
+ <framework value="pytorch" />
104
+ <is_python_object value="True" />
105
+ </conversion_parameters>
106
+ </rt_info>
107
+ </net>
openvino_vision_embeddings_merger_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba5140348a79b0b83c92ce101cbd5ff89bf470b407decc2303a8232a3d5513d
3
+ size 350515948
openvino_vision_embeddings_merger_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_vision_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2130223a20836875047edfe23b858ca1ba4e9582f8a165628bd43322f0391600
3
+ size 3010616
openvino_vision_embeddings_model.xml ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model3" version="11">
3
+ <layers>
4
+ <layer id="0" name="hidden_states" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="hidden_states">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Constant_1793" type="Const" version="opset1">
14
+ <data element_type="i64" shape="5" offset="0" size="40" />
15
+ <rt_info>
16
+ <attribute name="precise" version="0" />
17
+ </rt_info>
18
+ <output>
19
+ <port id="0" precision="I64" names="8">
20
+ <dim>5</dim>
21
+ </port>
22
+ </output>
23
+ </layer>
24
+ <layer id="2" name="aten::view/Reshape" type="Reshape" version="opset1">
25
+ <data special_zero="false" />
26
+ <input>
27
+ <port id="0" precision="FP32">
28
+ <dim>-1</dim>
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="1" precision="I64">
32
+ <dim>5</dim>
33
+ </port>
34
+ </input>
35
+ <output>
36
+ <port id="2" precision="FP32" names="14,9,hidden_states">
37
+ <dim>-1</dim>
38
+ <dim>3</dim>
39
+ <dim>2</dim>
40
+ <dim>14</dim>
41
+ <dim>14</dim>
42
+ </port>
43
+ </output>
44
+ </layer>
45
+ <layer id="3" name="self.proj.weight_compressed" type="Const" version="opset1">
46
+ <data element_type="f16" shape="1280, 3, 2, 14, 14" offset="40" size="3010560" />
47
+ <output>
48
+ <port id="0" precision="FP16" names="self.proj.weight">
49
+ <dim>1280</dim>
50
+ <dim>3</dim>
51
+ <dim>2</dim>
52
+ <dim>14</dim>
53
+ <dim>14</dim>
54
+ </port>
55
+ </output>
56
+ </layer>
57
+ <layer id="4" name="self.proj.weight" type="Convert" version="opset1">
58
+ <data destination_type="f32" />
59
+ <rt_info>
60
+ <attribute name="decompression" version="0" />
61
+ </rt_info>
62
+ <input>
63
+ <port id="0" precision="FP16">
64
+ <dim>1280</dim>
65
+ <dim>3</dim>
66
+ <dim>2</dim>
67
+ <dim>14</dim>
68
+ <dim>14</dim>
69
+ </port>
70
+ </input>
71
+ <output>
72
+ <port id="1" precision="FP32">
73
+ <dim>1280</dim>
74
+ <dim>3</dim>
75
+ <dim>2</dim>
76
+ <dim>14</dim>
77
+ <dim>14</dim>
78
+ </port>
79
+ </output>
80
+ </layer>
81
+ <layer id="5" name="__module.proj/aten::_convolution/Convolution" type="Convolution" version="opset1">
82
+ <data strides="2, 14, 14" dilations="1, 1, 1" pads_begin="0, 0, 0" pads_end="0, 0, 0" auto_pad="explicit" />
83
+ <input>
84
+ <port id="0" precision="FP32">
85
+ <dim>-1</dim>
86
+ <dim>3</dim>
87
+ <dim>2</dim>
88
+ <dim>14</dim>
89
+ <dim>14</dim>
90
+ </port>
91
+ <port id="1" precision="FP32">
92
+ <dim>1280</dim>
93
+ <dim>3</dim>
94
+ <dim>2</dim>
95
+ <dim>14</dim>
96
+ <dim>14</dim>
97
+ </port>
98
+ </input>
99
+ <output>
100
+ <port id="2" precision="FP32" names="32">
101
+ <dim>-1</dim>
102
+ <dim>1280</dim>
103
+ <dim>1</dim>
104
+ <dim>1</dim>
105
+ <dim>1</dim>
106
+ </port>
107
+ </output>
108
+ </layer>
109
+ <layer id="6" name="Constant_1840" type="Const" version="opset1">
110
+ <data element_type="i64" shape="2" offset="3010600" size="16" />
111
+ <rt_info>
112
+ <attribute name="precise" version="0" />
113
+ </rt_info>
114
+ <output>
115
+ <port id="0" precision="I64" names="18">
116
+ <dim>2</dim>
117
+ </port>
118
+ </output>
119
+ </layer>
120
+ <layer id="7" name="aten::view/Reshape_1" type="Reshape" version="opset1">
121
+ <data special_zero="false" />
122
+ <input>
123
+ <port id="0" precision="FP32">
124
+ <dim>-1</dim>
125
+ <dim>1280</dim>
126
+ <dim>1</dim>
127
+ <dim>1</dim>
128
+ <dim>1</dim>
129
+ </port>
130
+ <port id="1" precision="I64">
131
+ <dim>2</dim>
132
+ </port>
133
+ </input>
134
+ <output>
135
+ <port id="2" precision="FP32">
136
+ <dim>-1</dim>
137
+ <dim>1280</dim>
138
+ </port>
139
+ </output>
140
+ </layer>
141
+ <layer id="8" name="Result_1842" type="Result" version="opset1">
142
+ <input>
143
+ <port id="0" precision="FP32">
144
+ <dim>-1</dim>
145
+ <dim>1280</dim>
146
+ </port>
147
+ </input>
148
+ </layer>
149
+ </layers>
150
+ <edges>
151
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
152
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
153
+ <edge from-layer="2" from-port="2" to-layer="5" to-port="0" />
154
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
155
+ <edge from-layer="4" from-port="1" to-layer="5" to-port="1" />
156
+ <edge from-layer="5" from-port="2" to-layer="7" to-port="0" />
157
+ <edge from-layer="6" from-port="0" to-layer="7" to-port="1" />
158
+ <edge from-layer="7" from-port="2" to-layer="8" to-port="0" />
159
+ </edges>
160
+ <rt_info>
161
+ <Runtime_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
162
+ <conversion_parameters>
163
+ <framework value="pytorch" />
164
+ <is_python_object value="True" />
165
+ </conversion_parameters>
166
+ </rt_info>
167
+ </net>
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
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": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff