Hugging Face's logo

lokinfey
/
Phi-3.5-vision-ov-int4

phi3_v
custom_code
Model card Files Community
lokinfey commited on
Commit
4fd3615
•
1 Parent(s): 9248478

init model

Browse files
Files changed (13) hide show
  1. config.json +150 -0
  2. embed_token.bin +3 -0
  3. embed_token.xml +107 -0
  4. image_embed.bin +3 -0
  5. image_embed.xml +0 -0
  6. img_projection.bin +3 -0
  7. img_projection.xml +264 -0
  8. language_model.bin +3 -0
  9. language_model.xml +0 -0
  10. preprocessor_config.json +21 -0
  11. special_tokens_map.json +36 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +412 -0
config.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3.5-vision-instruct",
3
+ "architectures": [
4
+ "Phi3VForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3.5-vision-instruct--configuration_phi3_v.Phi3VConfig",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3.5-vision-instruct--modeling_phi3_v.Phi3VForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_layer": {
13
+ "embedding_cls": "image",
14
+ "hd_transform_order": "sub_glb",
15
+ "projection_cls": "mlp",
16
+ "use_hd_transform": true,
17
+ "with_learnable_separator": true
18
+ },
19
+ "embd_pdrop": 0.0,
20
+ "eos_token_id": 2,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 3072,
23
+ "img_processor": {
24
+ "image_dim_out": 1024,
25
+ "model_name": "openai/clip-vit-large-patch14-336",
26
+ "name": "clip_vision_model",
27
+ "num_img_tokens": 144
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 8192,
31
+ "max_position_embeddings": 131072,
32
+ "model_type": "phi3_v",
33
+ "num_attention_heads": 32,
34
+ "num_hidden_layers": 32,
35
+ "num_key_value_heads": 32,
36
+ "original_max_position_embeddings": 4096,
37
+ "pad_token_id": 32000,
38
+ "resid_pdrop": 0.0,
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": {
41
+ "long_factor": [
42
+ 1.0800000429153442,
43
+ 1.1100000143051147,
44
+ 1.1399999856948853,
45
+ 1.340000033378601,
46
+ 1.5899999141693115,
47
+ 1.600000023841858,
48
+ 1.6200000047683716,
49
+ 2.620000123977661,
50
+ 3.2300000190734863,
51
+ 3.2300000190734863,
52
+ 4.789999961853027,
53
+ 7.400000095367432,
54
+ 7.700000286102295,
55
+ 9.09000015258789,
56
+ 12.199999809265137,
57
+ 17.670000076293945,
58
+ 24.46000099182129,
59
+ 28.57000160217285,
60
+ 30.420001983642578,
61
+ 30.840002059936523,
62
+ 32.590003967285156,
63
+ 32.93000411987305,
64
+ 42.320003509521484,
65
+ 44.96000289916992,
66
+ 50.340003967285156,
67
+ 50.45000457763672,
68
+ 57.55000305175781,
69
+ 57.93000411987305,
70
+ 58.21000289916992,
71
+ 60.1400032043457,
72
+ 62.61000442504883,
73
+ 62.62000274658203,
74
+ 62.71000289916992,
75
+ 63.1400032043457,
76
+ 63.1400032043457,
77
+ 63.77000427246094,
78
+ 63.93000411987305,
79
+ 63.96000289916992,
80
+ 63.970001220703125,
81
+ 64.02999877929688,
82
+ 64.06999969482422,
83
+ 64.08000183105469,
84
+ 64.12000274658203,
85
+ 64.41000366210938,
86
+ 64.4800033569336,
87
+ 64.51000213623047,
88
+ 64.52999877929688,
89
+ 64.83999633789062
90
+ ],
91
+ "short_factor": [
92
+ 1.08,
93
+ 1.1,
94
+ 1.1300000000000001,
95
+ 1.2800000000000002,
96
+ 1.3100000000000003,
97
+ 1.4500000000000004,
98
+ 1.4500000000000004,
99
+ 1.9500000000000008,
100
+ 2.030000000000001,
101
+ 2.4299999999999926,
102
+ 2.5699999999999896,
103
+ 2.9499999999999815,
104
+ 3.729999999999965,
105
+ 3.869999999999962,
106
+ 4.189999999999955,
107
+ 4.43999999999995,
108
+ 4.6399999999999455,
109
+ 4.979999999999938,
110
+ 5.159999999999934,
111
+ 5.279999999999932,
112
+ 5.759999999999922,
113
+ 5.889999999999919,
114
+ 5.889999999999919,
115
+ 5.969999999999917,
116
+ 6.089999999999915,
117
+ 6.2799999999999105,
118
+ 6.7699999999999,
119
+ 6.8899999999998975,
120
+ 7.109999999999893,
121
+ 7.129999999999892,
122
+ 7.179999999999891,
123
+ 7.289999999999889,
124
+ 7.339999999999888,
125
+ 7.559999999999883,
126
+ 7.619999999999882,
127
+ 7.69999999999988,
128
+ 7.879999999999876,
129
+ 7.879999999999876,
130
+ 7.879999999999876,
131
+ 7.939999999999875,
132
+ 7.949999999999875,
133
+ 7.979999999999874,
134
+ 8.19999999999987,
135
+ 8.439999999999864,
136
+ 8.469999999999864,
137
+ 8.589999999999861,
138
+ 8.809999999999857,
139
+ 8.999999999999853
140
+ ],
141
+ "type": "su"
142
+ },
143
+ "rope_theta": 10000.0,
144
+ "sliding_window": 262144,
145
+ "tie_word_embeddings": false,
146
+ "torch_dtype": "bfloat16",
147
+ "transformers_version": "4.41.2",
148
+ "use_cache": true,
149
+ "vocab_size": 32064
150
+ }
embed_token.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0fc37f3cd84cf9313a7525875c2a02485ea1aa662d8cb3f4c807ddffd3357f
3
+ size 197001220
embed_token.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="32064, 3072" offset="0" size="197001216" />
15
+ <output>
16
+ <port id="0" precision="FP16" names="self.weight">
17
+ <dim>32064</dim>
18
+ <dim>3072</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>32064</dim>
30
+ <dim>3072</dim>
31
+ </port>
32
+ </input>
33
+ <output>
34
+ <port id="1" precision="FP32">
35
+ <dim>32064</dim>
36
+ <dim>3072</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="197001216" 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>32064</dim>
66
+ <dim>3072</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>3072</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>3072</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="2024.4.0-16311-2c8fd1e6e97" />
102
+ <conversion_parameters>
103
+ <framework value="pytorch" />
104
+ <is_python_object value="True" />
105
+ </conversion_parameters>
106
+ </rt_info>
107
+ </net>
image_embed.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24ff6a24c755ebeeed2fc19035b0229ad65ee5f282bec2b037f0e1d0a797da5
3
+ size 581818562
image_embed.xml ADDED
The diff for this file is too large to render. See raw diff
 
img_projection.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba191044550da50168cd99e4ebc43d0328de09f79ad6aac194914c337cbed742
3
+ size 44052480
img_projection.xml ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model6" version="11">
3
+ <layers>
4
+ <layer id="0" name="input" type="Parameter" version="opset1">
5
+ <data shape="?,?,?" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="input">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ <dim>-1</dim>
11
+ </port>
12
+ </output>
13
+ </layer>
14
+ <layer id="1" name="self.0.weight_compressed" type="Const" version="opset1">
15
+ <data element_type="f16" shape="3072, 4096" offset="0" size="25165824" />
16
+ <output>
17
+ <port id="0" precision="FP16" names="self.0.weight">
18
+ <dim>3072</dim>
19
+ <dim>4096</dim>
20
+ </port>
21
+ </output>
22
+ </layer>
23
+ <layer id="2" name="self.0.weight" type="Convert" version="opset1">
24
+ <data destination_type="f32" />
25
+ <rt_info>
26
+ <attribute name="decompression" version="0" />
27
+ </rt_info>
28
+ <input>
29
+ <port id="0" precision="FP16">
30
+ <dim>3072</dim>
31
+ <dim>4096</dim>
32
+ </port>
33
+ </input>
34
+ <output>
35
+ <port id="1" precision="FP32">
36
+ <dim>3072</dim>
37
+ <dim>4096</dim>
38
+ </port>
39
+ </output>
40
+ </layer>
41
+ <layer id="3" name="__module.0/aten::linear/MatMul" type="MatMul" version="opset1">
42
+ <data transpose_a="false" transpose_b="true" />
43
+ <input>
44
+ <port id="0" precision="FP32">
45
+ <dim>-1</dim>
46
+ <dim>-1</dim>
47
+ <dim>-1</dim>
48
+ </port>
49
+ <port id="1" precision="FP32">
50
+ <dim>3072</dim>
51
+ <dim>4096</dim>
52
+ </port>
53
+ </input>
54
+ <output>
55
+ <port id="2" precision="FP32">
56
+ <dim>-1</dim>
57
+ <dim>-1</dim>
58
+ <dim>3072</dim>
59
+ </port>
60
+ </output>
61
+ </layer>
62
+ <layer id="4" name="Constant_82325_compressed" type="Const" version="opset1">
63
+ <data element_type="f16" shape="1, 1, 3072" offset="25165824" size="6144" />
64
+ <output>
65
+ <port id="0" precision="FP16">
66
+ <dim>1</dim>
67
+ <dim>1</dim>
68
+ <dim>3072</dim>
69
+ </port>
70
+ </output>
71
+ </layer>
72
+ <layer id="5" name="Constant_82325" type="Convert" version="opset1">
73
+ <data destination_type="f32" />
74
+ <rt_info>
75
+ <attribute name="decompression" version="0" />
76
+ </rt_info>
77
+ <input>
78
+ <port id="0" precision="FP16">
79
+ <dim>1</dim>
80
+ <dim>1</dim>
81
+ <dim>3072</dim>
82
+ </port>
83
+ </input>
84
+ <output>
85
+ <port id="1" precision="FP32">
86
+ <dim>1</dim>
87
+ <dim>1</dim>
88
+ <dim>3072</dim>
89
+ </port>
90
+ </output>
91
+ </layer>
92
+ <layer id="6" name="__module.0/aten::linear/Add" type="Add" version="opset1">
93
+ <data auto_broadcast="numpy" />
94
+ <input>
95
+ <port id="0" precision="FP32">
96
+ <dim>-1</dim>
97
+ <dim>-1</dim>
98
+ <dim>3072</dim>
99
+ </port>
100
+ <port id="1" precision="FP32">
101
+ <dim>1</dim>
102
+ <dim>1</dim>
103
+ <dim>3072</dim>
104
+ </port>
105
+ </input>
106
+ <output>
107
+ <port id="2" precision="FP32" names="10">
108
+ <dim>-1</dim>
109
+ <dim>-1</dim>
110
+ <dim>3072</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="7" name="__module.1/aten::gelu/Gelu" type="Gelu" version="opset7">
115
+ <data approximation_mode="ERF" />
116
+ <input>
117
+ <port id="0" precision="FP32">
118
+ <dim>-1</dim>
119
+ <dim>-1</dim>
120
+ <dim>3072</dim>
121
+ </port>
122
+ </input>
123
+ <output>
124
+ <port id="1" precision="FP32" names="12">
125
+ <dim>-1</dim>
126
+ <dim>-1</dim>
127
+ <dim>3072</dim>
128
+ </port>
129
+ </output>
130
+ </layer>
131
+ <layer id="8" name="self.2.weight_compressed" type="Const" version="opset1">
132
+ <data element_type="f16" shape="3072, 3072" offset="25171968" size="18874368" />
133
+ <output>
134
+ <port id="0" precision="FP16" names="self.2.weight">
135
+ <dim>3072</dim>
136
+ <dim>3072</dim>
137
+ </port>
138
+ </output>
139
+ </layer>
140
+ <layer id="9" name="self.2.weight" type="Convert" version="opset1">
141
+ <data destination_type="f32" />
142
+ <rt_info>
143
+ <attribute name="decompression" version="0" />
144
+ </rt_info>
145
+ <input>
146
+ <port id="0" precision="FP16">
147
+ <dim>3072</dim>
148
+ <dim>3072</dim>
149
+ </port>
150
+ </input>
151
+ <output>
152
+ <port id="1" precision="FP32">
153
+ <dim>3072</dim>
154
+ <dim>3072</dim>
155
+ </port>
156
+ </output>
157
+ </layer>
158
+ <layer id="10" name="__module.2/aten::linear/MatMul" type="MatMul" version="opset1">
159
+ <data transpose_a="false" transpose_b="true" />
160
+ <input>
161
+ <port id="0" precision="FP32">
162
+ <dim>-1</dim>
163
+ <dim>-1</dim>
164
+ <dim>3072</dim>
165
+ </port>
166
+ <port id="1" precision="FP32">
167
+ <dim>3072</dim>
168
+ <dim>3072</dim>
169
+ </port>
170
+ </input>
171
+ <output>
172
+ <port id="2" precision="FP32">
173
+ <dim>-1</dim>
174
+ <dim>-1</dim>
175
+ <dim>3072</dim>
176
+ </port>
177
+ </output>
178
+ </layer>
179
+ <layer id="11" name="Constant_82326_compressed" type="Const" version="opset1">
180
+ <data element_type="f16" shape="1, 1, 3072" offset="44046336" size="6144" />
181
+ <output>
182
+ <port id="0" precision="FP16">
183
+ <dim>1</dim>
184
+ <dim>1</dim>
185
+ <dim>3072</dim>
186
+ </port>
187
+ </output>
188
+ </layer>
189
+ <layer id="12" name="Constant_82326" type="Convert" version="opset1">
190
+ <data destination_type="f32" />
191
+ <rt_info>
192
+ <attribute name="decompression" version="0" />
193
+ </rt_info>
194
+ <input>
195
+ <port id="0" precision="FP16">
196
+ <dim>1</dim>
197
+ <dim>1</dim>
198
+ <dim>3072</dim>
199
+ </port>
200
+ </input>
201
+ <output>
202
+ <port id="1" precision="FP32">
203
+ <dim>1</dim>
204
+ <dim>1</dim>
205
+ <dim>3072</dim>
206
+ </port>
207
+ </output>
208
+ </layer>
209
+ <layer id="13" name="__module.2/aten::linear/Add" type="Add" version="opset1">
210
+ <data auto_broadcast="numpy" />
211
+ <input>
212
+ <port id="0" precision="FP32">
213
+ <dim>-1</dim>
214
+ <dim>-1</dim>
215
+ <dim>3072</dim>
216
+ </port>
217
+ <port id="1" precision="FP32">
218
+ <dim>1</dim>
219
+ <dim>1</dim>
220
+ <dim>3072</dim>
221
+ </port>
222
+ </input>
223
+ <output>
224
+ <port id="2" precision="FP32">
225
+ <dim>-1</dim>
226
+ <dim>-1</dim>
227
+ <dim>3072</dim>
228
+ </port>
229
+ </output>
230
+ </layer>
231
+ <layer id="14" name="Result_80636" type="Result" version="opset1">
232
+ <input>
233
+ <port id="0" precision="FP32">
234
+ <dim>-1</dim>
235
+ <dim>-1</dim>
236
+ <dim>3072</dim>
237
+ </port>
238
+ </input>
239
+ </layer>
240
+ </layers>
241
+ <edges>
242
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
243
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
244
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
245
+ <edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
246
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
247
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
248
+ <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
249
+ <edge from-layer="7" from-port="1" to-layer="10" to-port="0" />
250
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="0" />
251
+ <edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
252
+ <edge from-layer="10" from-port="2" to-layer="13" to-port="0" />
253
+ <edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
254
+ <edge from-layer="12" from-port="1" to-layer="13" to-port="1" />
255
+ <edge from-layer="13" from-port="2" to-layer="14" to-port="0" />
256
+ </edges>
257
+ <rt_info>
258
+ <Runtime_version value="2024.4.0-16311-2c8fd1e6e97" />
259
+ <conversion_parameters>
260
+ <framework value="pytorch" />
261
+ <is_python_object value="True" />
262
+ </conversion_parameters>
263
+ </rt_info>
264
+ </net>
language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b1f3f600c143a143bc11f7fd8417ff406238ab2602bd151c9c6c68a70ad4de
3
+ size 2711680386
language_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VImageProcessor",
4
+ "AutoProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VProcessor"
5
+ },
6
+ "do_convert_rgb": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Phi3VImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "num_crops": 4,
19
+ "num_img_tokens": 144,
20
+ "processor_class": "Phi3VProcessor"
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|end|>",
5
+ "<|user|>",
6
+ "<|end|>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,412 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|placeholder7|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|placeholder8|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|placeholder9|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|placeholder10|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|placeholder11|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|placeholder12|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|placeholder13|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|placeholder14|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|placeholder15|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|placeholder16|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|placeholder17|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|placeholder18|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|placeholder19|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|placeholder20|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|placeholder21|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|placeholder22|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|placeholder23|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|placeholder24|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|placeholder25|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|placeholder26|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|placeholder27|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|placeholder28|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|placeholder29|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|placeholder30|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|placeholder31|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|placeholder32|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|placeholder33|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "32038": {
334
+ "content": "<|placeholder34|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": true,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "32039": {
342
+ "content": "<|placeholder35|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": true,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "32040": {
350
+ "content": "<|placeholder36|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": true,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "32041": {
358
+ "content": "<|placeholder37|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": true,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "32042": {
366
+ "content": "<|placeholder38|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": true,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "32043": {
374
+ "content": "<|placeholder39|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": true,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "32044": {
382
+ "content": "<|image|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": true,
386
+ "single_word": false,
387
+ "special": true
388
+ }
389
+ },
390
+ "additional_special_tokens": [
391
+ "<|system|>",
392
+ "<|end|>",
393
+ "<|user|>",
394
+ "<|end|>"
395
+ ],
396
+ "auto_map": {
397
+ "AutoProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VProcessor"
398
+ },
399
+ "bos_token": "<s>",
400
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
401
+ "clean_up_tokenization_spaces": false,
402
+ "eos_token": "<|endoftext|>",
403
+ "legacy": false,
404
+ "model_max_length": 131072,
405
+ "pad_token": "<|endoftext|>",
406
+ "padding_side": "right",
407
+ "processor_class": "Phi3VProcessor",
408
+ "sp_model_kwargs": {},
409
+ "tokenizer_class": "LlamaTokenizer",
410
+ "unk_token": "<unk>",
411
+ "use_default_system_prompt": false
412
+ }