Hugging Face's logo

llmware
/
unitary-toxic-roberta-ov

OpenVINO
roberta
green
p1
llmware-encoder
ov
Model card Files Community
doberst commited on
Commit
b952472
•
1 Parent(s): 9f536ba

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +65 -0
  2. merges.txt +0 -0
  3. openvino_detokenizer.bin +3 -0
  4. openvino_detokenizer.xml +219 -0
  5. openvino_model.bin +3 -0
  6. openvino_model.xml +0 -0
  7. openvino_tokenizer.bin +3 -0
  8. openvino_tokenizer.xml +668 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +57 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unitary/unbiased-toxic-roberta",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "function_to_apply": "sigmoid",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "toxicity",
17
+ "1": "severe_toxicity",
18
+ "2": "obscene",
19
+ "3": "identity_attack",
20
+ "4": "insult",
21
+ "5": "threat",
22
+ "6": "sexual_explicit",
23
+ "7": "male",
24
+ "8": "female",
25
+ "9": "homosexual_gay_or_lesbian",
26
+ "10": "christian",
27
+ "11": "jewish",
28
+ "12": "muslim",
29
+ "13": "black",
30
+ "14": "white",
31
+ "15": "psychiatric_or_mental_illness"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "black": 13,
37
+ "christian": 10,
38
+ "female": 8,
39
+ "homosexual_gay_or_lesbian": 9,
40
+ "identity_attack": 3,
41
+ "insult": 4,
42
+ "jewish": 11,
43
+ "male": 7,
44
+ "muslim": 12,
45
+ "obscene": 2,
46
+ "psychiatric_or_mental_illness": 15,
47
+ "severe_toxicity": 1,
48
+ "sexual_explicit": 6,
49
+ "threat": 5,
50
+ "toxicity": 0,
51
+ "white": 14
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "max_position_embeddings": 514,
55
+ "model_type": "roberta",
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "pad_token_id": 1,
59
+ "position_embedding_type": "absolute",
60
+ "problem_type": "multi_label_classification",
61
+ "transformers_version": "4.41.2",
62
+ "type_vocab_size": 1,
63
+ "use_cache": true,
64
+ "vocab_size": 50265
65
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e74e4c74704d16b2216ffe9d8c37905b2901b03913d8aa9f9f4ad0cfcc9e8c
3
+ size 557917
openvino_detokenizer.xml ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_10539" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_10539">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_10555" type="Convert" version="opset1">
14
+ <data destination_type="i32" />
15
+ <input>
16
+ <port id="0" precision="I64">
17
+ <dim>-1</dim>
18
+ <dim>-1</dim>
19
+ </port>
20
+ </input>
21
+ <output>
22
+ <port id="1" precision="I32">
23
+ <dim>-1</dim>
24
+ <dim>-1</dim>
25
+ </port>
26
+ </output>
27
+ </layer>
28
+ <layer id="2" name="Constant_10510" type="Const" version="opset1">
29
+ <data element_type="u8" shape="557868" offset="0" size="557868" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>557868</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_10511" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>557868</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I32">
45
+ <dim>-1</dim>
46
+ </port>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="U8">
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="VocabDecoder_10540" type="VocabDecoder" version="extension">
56
+ <data skip_tokens="0, 1, 2, 3, 50264" />
57
+ <input>
58
+ <port id="0" precision="I32">
59
+ <dim>-1</dim>
60
+ <dim>-1</dim>
61
+ </port>
62
+ <port id="1" precision="I32">
63
+ <dim>-1</dim>
64
+ </port>
65
+ <port id="2" precision="I32">
66
+ <dim>-1</dim>
67
+ </port>
68
+ <port id="3" precision="U8">
69
+ <dim>-1</dim>
70
+ </port>
71
+ </input>
72
+ <output>
73
+ <port id="4" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ <port id="5" precision="I32">
77
+ <dim>-1</dim>
78
+ </port>
79
+ <port id="6" precision="I32">
80
+ <dim>-1</dim>
81
+ </port>
82
+ <port id="7" precision="I32">
83
+ <dim>-1</dim>
84
+ </port>
85
+ <port id="8" precision="U8">
86
+ <dim>-1</dim>
87
+ </port>
88
+ </output>
89
+ </layer>
90
+ <layer id="5" name="CharsToBytes_10541" type="CharsToBytes" version="extension">
91
+ <input>
92
+ <port id="0" precision="I32">
93
+ <dim>-1</dim>
94
+ </port>
95
+ <port id="1" precision="I32">
96
+ <dim>-1</dim>
97
+ </port>
98
+ <port id="2" precision="I32">
99
+ <dim>-1</dim>
100
+ </port>
101
+ <port id="3" precision="I32">
102
+ <dim>-1</dim>
103
+ </port>
104
+ <port id="4" precision="U8">
105
+ <dim>-1</dim>
106
+ </port>
107
+ </input>
108
+ <output>
109
+ <port id="5" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ <port id="6" precision="I32">
113
+ <dim>-1</dim>
114
+ </port>
115
+ <port id="7" precision="U8">
116
+ <dim>-1</dim>
117
+ </port>
118
+ </output>
119
+ </layer>
120
+ <layer id="6" name="Constant_10543" type="Const" version="opset1">
121
+ <data element_type="u8" shape="47" offset="557868" size="47" />
122
+ <output>
123
+ <port id="0" precision="U8">
124
+ <dim>47</dim>
125
+ </port>
126
+ </output>
127
+ </layer>
128
+ <layer id="7" name="Constant_10545" type="Const" version="opset1">
129
+ <data element_type="u8" shape="2" offset="557915" size="2" />
130
+ <output>
131
+ <port id="0" precision="U8">
132
+ <dim>2</dim>
133
+ </port>
134
+ </output>
135
+ </layer>
136
+ <layer id="8" name="RegexNormalization_10546" type="RegexNormalization" version="extension">
137
+ <data global_replace="true" />
138
+ <input>
139
+ <port id="0" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="1" precision="I32">
143
+ <dim>-1</dim>
144
+ </port>
145
+ <port id="2" precision="U8">
146
+ <dim>-1</dim>
147
+ </port>
148
+ <port id="3" precision="U8">
149
+ <dim>47</dim>
150
+ </port>
151
+ <port id="4" precision="U8">
152
+ <dim>2</dim>
153
+ </port>
154
+ </input>
155
+ <output>
156
+ <port id="5" precision="I32">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="6" precision="I32">
160
+ <dim>-1</dim>
161
+ </port>
162
+ <port id="7" precision="U8">
163
+ <dim>-1</dim>
164
+ </port>
165
+ </output>
166
+ </layer>
167
+ <layer id="9" name="StringTensorPack_10547" type="StringTensorPack" version="extension">
168
+ <data mode="begins_ends" />
169
+ <input>
170
+ <port id="0" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="1" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="2" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ </input>
180
+ <output>
181
+ <port id="3" precision="STRING" names="string_output">
182
+ <dim>-1</dim>
183
+ </port>
184
+ </output>
185
+ </layer>
186
+ <layer id="10" name="Result_10548" type="Result" version="opset1">
187
+ <input>
188
+ <port id="0" precision="STRING">
189
+ <dim>-1</dim>
190
+ </port>
191
+ </input>
192
+ </layer>
193
+ </layers>
194
+ <edges>
195
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
196
+ <edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
197
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
198
+ <edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
199
+ <edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
200
+ <edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
201
+ <edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
202
+ <edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
203
+ <edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
204
+ <edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
205
+ <edge from-layer="4" from-port="8" to-layer="5" to-port="4" />
206
+ <edge from-layer="5" from-port="5" to-layer="8" to-port="0" />
207
+ <edge from-layer="5" from-port="6" to-layer="8" to-port="1" />
208
+ <edge from-layer="5" from-port="7" to-layer="8" to-port="2" />
209
+ <edge from-layer="6" from-port="0" to-layer="8" to-port="3" />
210
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="4" />
211
+ <edge from-layer="8" from-port="5" to-layer="9" to-port="0" />
212
+ <edge from-layer="8" from-port="6" to-layer="9" to-port="1" />
213
+ <edge from-layer="8" from-port="7" to-layer="9" to-port="2" />
214
+ <edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
215
+ </edges>
216
+ <rt_info>
217
+ <eos_token_id value="2" />
218
+ </rt_info>
219
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53ee011c766c17e59b63f0c230918fc58eeb4556cfaecc4d66ba13a4e23c640
3
+ size 92660056
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c791f1cbd265b33115089c93f451507a28d88173539e752fc7912efe3c8152c
3
+ size 1164280
openvino_tokenizer.xml ADDED
@@ -0,0 +1,668 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_10429" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_10429">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_10520" type="Const" version="opset1">
13
+ <data element_type="i32" shape="" offset="0" size="4" />
14
+ <output>
15
+ <port id="0" precision="I32" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="Constant_10521" type="Const" version="opset1">
19
+ <data element_type="i32" shape="" offset="4" size="4" />
20
+ <output>
21
+ <port id="0" precision="I32" />
22
+ </output>
23
+ </layer>
24
+ <layer id="3" name="Constant_10522" type="Const" version="opset1">
25
+ <data element_type="i32" shape="1" offset="0" size="4" />
26
+ <output>
27
+ <port id="0" precision="I32">
28
+ <dim>1</dim>
29
+ </port>
30
+ </output>
31
+ </layer>
32
+ <layer id="4" name="Constant_10435" type="Const" version="opset1">
33
+ <data element_type="i32" shape="" offset="0" size="4" />
34
+ <output>
35
+ <port id="0" precision="I32" />
36
+ </output>
37
+ </layer>
38
+ <layer id="5" name="StringTensorUnpack_10430" type="StringTensorUnpack" version="extension">
39
+ <data mode="begins_ends" />
40
+ <input>
41
+ <port id="0" precision="STRING">
42
+ <dim>-1</dim>
43
+ </port>
44
+ </input>
45
+ <output>
46
+ <port id="1" precision="I32">
47
+ <dim>-1</dim>
48
+ </port>
49
+ <port id="2" precision="I32">
50
+ <dim>-1</dim>
51
+ </port>
52
+ <port id="3" precision="U8">
53
+ <dim>-1</dim>
54
+ </port>
55
+ </output>
56
+ </layer>
57
+ <layer id="6" name="ShapeOf_10431" type="ShapeOf" version="opset3">
58
+ <data output_type="i64" />
59
+ <input>
60
+ <port id="0" precision="I32">
61
+ <dim>-1</dim>
62
+ </port>
63
+ </input>
64
+ <output>
65
+ <port id="1" precision="I64">
66
+ <dim>1</dim>
67
+ </port>
68
+ </output>
69
+ </layer>
70
+ <layer id="7" name="Constant_10432" type="Const" version="opset1">
71
+ <data element_type="i32" shape="" offset="0" size="4" />
72
+ <output>
73
+ <port id="0" precision="I32" />
74
+ </output>
75
+ </layer>
76
+ <layer id="8" name="Constant_10433" type="Const" version="opset1">
77
+ <data element_type="i32" shape="" offset="0" size="4" />
78
+ <output>
79
+ <port id="0" precision="I32" />
80
+ </output>
81
+ </layer>
82
+ <layer id="9" name="Gather_10434" type="Gather" version="opset8">
83
+ <data batch_dims="0" />
84
+ <input>
85
+ <port id="0" precision="I64">
86
+ <dim>1</dim>
87
+ </port>
88
+ <port id="1" precision="I32" />
89
+ <port id="2" precision="I32" />
90
+ </input>
91
+ <output>
92
+ <port id="3" precision="I64" />
93
+ </output>
94
+ </layer>
95
+ <layer id="10" name="Constant_10436" type="Const" version="opset1">
96
+ <data element_type="i32" shape="" offset="4" size="4" />
97
+ <output>
98
+ <port id="0" precision="I32" />
99
+ </output>
100
+ </layer>
101
+ <layer id="11" name="Range_10437" type="Range" version="opset4">
102
+ <data output_type="i32" />
103
+ <input>
104
+ <port id="0" precision="I32" />
105
+ <port id="1" precision="I64" />
106
+ <port id="2" precision="I32" />
107
+ </input>
108
+ <output>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="12" name="Constant_10439" type="Const" version="opset1">
115
+ <data element_type="i32" shape="" offset="4" size="4" />
116
+ <output>
117
+ <port id="0" precision="I32" />
118
+ </output>
119
+ </layer>
120
+ <layer id="13" name="Constant_10440" type="Const" version="opset1">
121
+ <data element_type="i64" shape="" offset="8" size="8" />
122
+ <output>
123
+ <port id="0" precision="I64" />
124
+ </output>
125
+ </layer>
126
+ <layer id="14" name="Add_10441" type="Add" version="opset1">
127
+ <data auto_broadcast="numpy" />
128
+ <input>
129
+ <port id="0" precision="I64" />
130
+ <port id="1" precision="I64" />
131
+ </input>
132
+ <output>
133
+ <port id="2" precision="I64" />
134
+ </output>
135
+ </layer>
136
+ <layer id="15" name="Constant_10442" type="Const" version="opset1">
137
+ <data element_type="i32" shape="" offset="4" size="4" />
138
+ <output>
139
+ <port id="0" precision="I32" />
140
+ </output>
141
+ </layer>
142
+ <layer id="16" name="Range_10443" type="Range" version="opset4">
143
+ <data output_type="i32" />
144
+ <input>
145
+ <port id="0" precision="I32" />
146
+ <port id="1" precision="I64" />
147
+ <port id="2" precision="I32" />
148
+ </input>
149
+ <output>
150
+ <port id="3" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ </output>
154
+ </layer>
155
+ <layer id="17" name="Constant_10506" type="Const" version="opset1">
156
+ <data element_type="u8" shape="64" offset="16" size="64" />
157
+ <output>
158
+ <port id="0" precision="U8">
159
+ <dim>64</dim>
160
+ </port>
161
+ </output>
162
+ </layer>
163
+ <layer id="18" name="RegexSplit_10507" type="RegexSplit" version="extension">
164
+ <data behaviour="isolate" invert="false" max_splits="-1" />
165
+ <input>
166
+ <port id="0" precision="I32">
167
+ <dim>-1</dim>
168
+ </port>
169
+ <port id="1" precision="I32">
170
+ <dim>-1</dim>
171
+ </port>
172
+ <port id="2" precision="I32">
173
+ <dim>-1</dim>
174
+ </port>
175
+ <port id="3" precision="I32">
176
+ <dim>-1</dim>
177
+ </port>
178
+ <port id="4" precision="U8">
179
+ <dim>-1</dim>
180
+ </port>
181
+ <port id="5" precision="U8">
182
+ <dim>64</dim>
183
+ </port>
184
+ </input>
185
+ <output>
186
+ <port id="6" precision="I32">
187
+ <dim>-1</dim>
188
+ </port>
189
+ <port id="7" precision="I32">
190
+ <dim>-1</dim>
191
+ </port>
192
+ <port id="8" precision="I32">
193
+ <dim>-1</dim>
194
+ </port>
195
+ <port id="9" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="10" precision="U8">
199
+ <dim>-1</dim>
200
+ </port>
201
+ </output>
202
+ </layer>
203
+ <layer id="19" name="BytesToChars_10508" type="BytesToChars" version="extension">
204
+ <input>
205
+ <port id="0" precision="I32">
206
+ <dim>-1</dim>
207
+ </port>
208
+ <port id="1" precision="I32">
209
+ <dim>-1</dim>
210
+ </port>
211
+ <port id="2" precision="I32">
212
+ <dim>-1</dim>
213
+ </port>
214
+ <port id="3" precision="I32">
215
+ <dim>-1</dim>
216
+ </port>
217
+ <port id="4" precision="U8">
218
+ <dim>-1</dim>
219
+ </port>
220
+ </input>
221
+ <output>
222
+ <port id="5" precision="I32">
223
+ <dim>-1</dim>
224
+ </port>
225
+ <port id="6" precision="I32">
226
+ <dim>-1</dim>
227
+ </port>
228
+ <port id="7" precision="I32">
229
+ <dim>-1</dim>
230
+ </port>
231
+ <port id="8" precision="I32">
232
+ <dim>-1</dim>
233
+ </port>
234
+ <port id="9" precision="U8">
235
+ <dim>-1</dim>
236
+ </port>
237
+ </output>
238
+ </layer>
239
+ <layer id="20" name="Constant_10510" type="Const" version="opset1">
240
+ <data element_type="u8" shape="557868" offset="80" size="557868" />
241
+ <output>
242
+ <port id="0" precision="U8">
243
+ <dim>557868</dim>
244
+ </port>
245
+ </output>
246
+ </layer>
247
+ <layer id="21" name="StringTensorUnpack_10511" type="StringTensorUnpack" version="extension">
248
+ <data mode="begins_ends" />
249
+ <input>
250
+ <port id="0" precision="U8">
251
+ <dim>557868</dim>
252
+ </port>
253
+ </input>
254
+ <output>
255
+ <port id="1" precision="I32">
256
+ <dim>-1</dim>
257
+ </port>
258
+ <port id="2" precision="I32">
259
+ <dim>-1</dim>
260
+ </port>
261
+ <port id="3" precision="U8">
262
+ <dim>-1</dim>
263
+ </port>
264
+ </output>
265
+ </layer>
266
+ <layer id="22" name="Constant_10513" type="Const" version="opset1">
267
+ <data element_type="u8" shape="606312" offset="557948" size="606312" />
268
+ <output>
269
+ <port id="0" precision="U8">
270
+ <dim>606312</dim>
271
+ </port>
272
+ </output>
273
+ </layer>
274
+ <layer id="23" name="StringTensorUnpack_10514" type="StringTensorUnpack" version="extension">
275
+ <data mode="begins_ends" />
276
+ <input>
277
+ <port id="0" precision="U8">
278
+ <dim>606312</dim>
279
+ </port>
280
+ </input>
281
+ <output>
282
+ <port id="1" precision="I32">
283
+ <dim>-1</dim>
284
+ </port>
285
+ <port id="2" precision="I32">
286
+ <dim>-1</dim>
287
+ </port>
288
+ <port id="3" precision="U8">
289
+ <dim>-1</dim>
290
+ </port>
291
+ </output>
292
+ </layer>
293
+ <layer id="24" name="BPETokenizer_10515" type="BPETokenizer" version="extension">
294
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" />
295
+ <input>
296
+ <port id="0" precision="I32">
297
+ <dim>-1</dim>
298
+ </port>
299
+ <port id="1" precision="I32">
300
+ <dim>-1</dim>
301
+ </port>
302
+ <port id="2" precision="I32">
303
+ <dim>-1</dim>
304
+ </port>
305
+ <port id="3" precision="I32">
306
+ <dim>-1</dim>
307
+ </port>
308
+ <port id="4" precision="U8">
309
+ <dim>-1</dim>
310
+ </port>
311
+ <port id="5" precision="I32">
312
+ <dim>-1</dim>
313
+ </port>
314
+ <port id="6" precision="I32">
315
+ <dim>-1</dim>
316
+ </port>
317
+ <port id="7" precision="U8">
318
+ <dim>-1</dim>
319
+ </port>
320
+ <port id="8" precision="I32">
321
+ <dim>-1</dim>
322
+ </port>
323
+ <port id="9" precision="I32">
324
+ <dim>-1</dim>
325
+ </port>
326
+ <port id="10" precision="U8">
327
+ <dim>-1</dim>
328
+ </port>
329
+ </input>
330
+ <output>
331
+ <port id="11" precision="I32">
332
+ <dim>-1</dim>
333
+ </port>
334
+ <port id="12" precision="I32">
335
+ <dim>-1</dim>
336
+ </port>
337
+ <port id="13" precision="I32">
338
+ <dim>-1</dim>
339
+ </port>
340
+ </output>
341
+ </layer>
342
+ <layer id="25" name="Subtract_10516" type="Subtract" version="opset1">
343
+ <data auto_broadcast="numpy" />
344
+ <input>
345
+ <port id="0" precision="I32">
346
+ <dim>-1</dim>
347
+ </port>
348
+ <port id="1" precision="I32">
349
+ <dim>-1</dim>
350
+ </port>
351
+ </input>
352
+ <output>
353
+ <port id="2" precision="I32">
354
+ <dim>-1</dim>
355
+ </port>
356
+ </output>
357
+ </layer>
358
+ <layer id="26" name="Constant_10517" type="Const" version="opset1">
359
+ <data element_type="i32" shape="" offset="1164260" size="4" />
360
+ <output>
361
+ <port id="0" precision="I32" />
362
+ </output>
363
+ </layer>
364
+ <layer id="27" name="Minimum_10518" type="Minimum" version="opset1">
365
+ <data auto_broadcast="numpy" />
366
+ <input>
367
+ <port id="0" precision="I32">
368
+ <dim>-1</dim>
369
+ </port>
370
+ <port id="1" precision="I32" />
371
+ </input>
372
+ <output>
373
+ <port id="2" precision="I32">
374
+ <dim>-1</dim>
375
+ </port>
376
+ </output>
377
+ </layer>
378
+ <layer id="28" name="Add_10519" type="Add" version="opset1">
379
+ <data auto_broadcast="numpy" />
380
+ <input>
381
+ <port id="0" precision="I32">
382
+ <dim>-1</dim>
383
+ </port>
384
+ <port id="1" precision="I32">
385
+ <dim>-1</dim>
386
+ </port>
387
+ </input>
388
+ <output>
389
+ <port id="2" precision="I32">
390
+ <dim>-1</dim>
391
+ </port>
392
+ </output>
393
+ </layer>
394
+ <layer id="29" name="Constant_10523" type="Const" version="opset1">
395
+ <data element_type="i32" shape="" offset="0" size="4" />
396
+ <output>
397
+ <port id="0" precision="I32" />
398
+ </output>
399
+ </layer>
400
+ <layer id="30" name="Constant_10524" type="Const" version="opset1">
401
+ <data element_type="i32" shape="" offset="4" size="4" />
402
+ <output>
403
+ <port id="0" precision="I32" />
404
+ </output>
405
+ </layer>
406
+ <layer id="31" name="Constant_10525" type="Const" version="opset1">
407
+ <data element_type="i32" shape="1" offset="1164264" size="4" />
408
+ <output>
409
+ <port id="0" precision="I32">
410
+ <dim>1</dim>
411
+ </port>
412
+ </output>
413
+ </layer>
414
+ <layer id="32" name="Constant_10526" type="Const" version="opset1">
415
+ <data element_type="i32" shape="3" offset="1164268" size="12" />
416
+ <output>
417
+ <port id="0" precision="I32">
418
+ <dim>3</dim>
419
+ </port>
420
+ </output>
421
+ </layer>
422
+ <layer id="33" name="CombineSegments_10527" type="CombineSegments" version="extension">
423
+ <input>
424
+ <port id="0" precision="I32" />
425
+ <port id="1" precision="I32" />
426
+ <port id="2" precision="I32">
427
+ <dim>1</dim>
428
+ </port>
429
+ <port id="3" precision="I32">
430
+ <dim>-1</dim>
431
+ </port>
432
+ <port id="4" precision="I32">
433
+ <dim>-1</dim>
434
+ </port>
435
+ <port id="5" precision="I32">
436
+ <dim>-1</dim>
437
+ </port>
438
+ <port id="6" precision="I32" />
439
+ <port id="7" precision="I32" />
440
+ <port id="8" precision="I32">
441
+ <dim>1</dim>
442
+ </port>
443
+ <port id="9" precision="I32">
444
+ <dim>3</dim>
445
+ </port>
446
+ </input>
447
+ <output>
448
+ <port id="10" precision="I32">
449
+ <dim>-1</dim>
450
+ </port>
451
+ <port id="11" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ <port id="12" precision="I32">
455
+ <dim>-1</dim>
456
+ </port>
457
+ <port id="13" precision="I32">
458
+ <dim>-1</dim>
459
+ </port>
460
+ <port id="14" precision="I32">
461
+ <dim>-1</dim>
462
+ </port>
463
+ <port id="15" precision="I32">
464
+ <dim>-1</dim>
465
+ </port>
466
+ </output>
467
+ </layer>
468
+ <layer id="34" name="Subtract_10528" type="Subtract" version="opset1">
469
+ <data auto_broadcast="numpy" />
470
+ <input>
471
+ <port id="0" precision="I32">
472
+ <dim>-1</dim>
473
+ </port>
474
+ <port id="1" precision="I32">
475
+ <dim>-1</dim>
476
+ </port>
477
+ </input>
478
+ <output>
479
+ <port id="2" precision="I32">
480
+ <dim>-1</dim>
481
+ </port>
482
+ </output>
483
+ </layer>
484
+ <layer id="35" name="Constant_10529" type="Const" version="opset1">
485
+ <data element_type="i32" shape="" offset="0" size="4" />
486
+ <output>
487
+ <port id="0" precision="I32" />
488
+ </output>
489
+ </layer>
490
+ <layer id="36" name="ReduceMax_10530" type="ReduceMax" version="opset1">
491
+ <data keep_dims="false" />
492
+ <input>
493
+ <port id="0" precision="I32">
494
+ <dim>-1</dim>
495
+ </port>
496
+ <port id="1" precision="I32" />
497
+ </input>
498
+ <output>
499
+ <port id="2" precision="I32" />
500
+ </output>
501
+ </layer>
502
+ <layer id="37" name="Constant_10531" type="Const" version="opset1">
503
+ <data element_type="i32" shape="" offset="4" size="4" />
504
+ <output>
505
+ <port id="0" precision="I32" />
506
+ </output>
507
+ </layer>
508
+ <layer id="38" name="RaggedToDense_10532" type="RaggedToDense" version="extension">
509
+ <data pad_right="true" />
510
+ <input>
511
+ <port id="0" precision="I32">
512
+ <dim>-1</dim>
513
+ </port>
514
+ <port id="1" precision="I32">
515
+ <dim>-1</dim>
516
+ </port>
517
+ <port id="2" precision="I32">
518
+ <dim>-1</dim>
519
+ </port>
520
+ <port id="3" precision="I32" />
521
+ <port id="4" precision="I32" />
522
+ </input>
523
+ <output>
524
+ <port id="5" precision="I32">
525
+ <dim>-1</dim>
526
+ <dim>-1</dim>
527
+ </port>
528
+ <port id="6" precision="BOOL">
529
+ <dim>-1</dim>
530
+ <dim>-1</dim>
531
+ </port>
532
+ </output>
533
+ </layer>
534
+ <layer id="39" name="Convert_10533" type="Convert" version="opset1">
535
+ <data destination_type="i32" />
536
+ <input>
537
+ <port id="0" precision="BOOL">
538
+ <dim>-1</dim>
539
+ <dim>-1</dim>
540
+ </port>
541
+ </input>
542
+ <output>
543
+ <port id="1" precision="I32">
544
+ <dim>-1</dim>
545
+ <dim>-1</dim>
546
+ </port>
547
+ </output>
548
+ </layer>
549
+ <layer id="40" name="Convert_10533" type="Convert" version="opset1">
550
+ <data destination_type="i64" />
551
+ <input>
552
+ <port id="0" precision="I32">
553
+ <dim>-1</dim>
554
+ <dim>-1</dim>
555
+ </port>
556
+ </input>
557
+ <output>
558
+ <port id="1" precision="I64" names="attention_mask">
559
+ <dim>-1</dim>
560
+ <dim>-1</dim>
561
+ </port>
562
+ </output>
563
+ </layer>
564
+ <layer id="42" name="RaggedToDense_10532.0" type="Convert" version="opset1">
565
+ <data destination_type="i64" />
566
+ <input>
567
+ <port id="0" precision="I32">
568
+ <dim>-1</dim>
569
+ <dim>-1</dim>
570
+ </port>
571
+ </input>
572
+ <output>
573
+ <port id="1" precision="I64" names="input_ids">
574
+ <dim>-1</dim>
575
+ <dim>-1</dim>
576
+ </port>
577
+ </output>
578
+ </layer>
579
+ <layer id="43" name="Result_10536" type="Result" version="opset1">
580
+ <input>
581
+ <port id="0" precision="I64">
582
+ <dim>-1</dim>
583
+ <dim>-1</dim>
584
+ </port>
585
+ </input>
586
+ </layer>
587
+ <layer id="41" name="Result_10538" type="Result" version="opset1">
588
+ <input>
589
+ <port id="0" precision="I64">
590
+ <dim>-1</dim>
591
+ <dim>-1</dim>
592
+ </port>
593
+ </input>
594
+ </layer>
595
+ </layers>
596
+ <edges>
597
+ <edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
598
+ <edge from-layer="1" from-port="0" to-layer="33" to-port="0" />
599
+ <edge from-layer="2" from-port="0" to-layer="33" to-port="1" />
600
+ <edge from-layer="3" from-port="0" to-layer="33" to-port="2" />
601
+ <edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
602
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
603
+ <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
604
+ <edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
605
+ <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
606
+ <edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
607
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
608
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
609
+ <edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
610
+ <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
611
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
612
+ <edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
613
+ <edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
614
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
615
+ <edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
616
+ <edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
617
+ <edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
618
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
619
+ <edge from-layer="18" from-port="6" to-layer="19" to-port="0" />
620
+ <edge from-layer="18" from-port="7" to-layer="19" to-port="1" />
621
+ <edge from-layer="18" from-port="8" to-layer="19" to-port="2" />
622
+ <edge from-layer="18" from-port="9" to-layer="19" to-port="3" />
623
+ <edge from-layer="18" from-port="10" to-layer="19" to-port="4" />
624
+ <edge from-layer="19" from-port="5" to-layer="24" to-port="0" />
625
+ <edge from-layer="19" from-port="6" to-layer="24" to-port="1" />
626
+ <edge from-layer="19" from-port="7" to-layer="24" to-port="2" />
627
+ <edge from-layer="19" from-port="8" to-layer="24" to-port="3" />
628
+ <edge from-layer="19" from-port="9" to-layer="24" to-port="4" />
629
+ <edge from-layer="20" from-port="0" to-layer="21" to-port="0" />
630
+ <edge from-layer="21" from-port="3" to-layer="24" to-port="7" />
631
+ <edge from-layer="21" from-port="1" to-layer="24" to-port="5" />
632
+ <edge from-layer="21" from-port="2" to-layer="24" to-port="6" />
633
+ <edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
634
+ <edge from-layer="23" from-port="1" to-layer="24" to-port="8" />
635
+ <edge from-layer="23" from-port="2" to-layer="24" to-port="9" />
636
+ <edge from-layer="23" from-port="3" to-layer="24" to-port="10" />
637
+ <edge from-layer="24" from-port="12" to-layer="25" to-port="0" />
638
+ <edge from-layer="24" from-port="11" to-layer="25" to-port="1" />
639
+ <edge from-layer="24" from-port="11" to-layer="28" to-port="0" />
640
+ <edge from-layer="24" from-port="11" to-layer="33" to-port="3" />
641
+ <edge from-layer="24" from-port="13" to-layer="33" to-port="5" />
642
+ <edge from-layer="25" from-port="2" to-layer="27" to-port="0" />
643
+ <edge from-layer="26" from-port="0" to-layer="27" to-port="1" />
644
+ <edge from-layer="27" from-port="2" to-layer="28" to-port="1" />
645
+ <edge from-layer="28" from-port="2" to-layer="33" to-port="4" />
646
+ <edge from-layer="29" from-port="0" to-layer="33" to-port="6" />
647
+ <edge from-layer="30" from-port="0" to-layer="33" to-port="7" />
648
+ <edge from-layer="31" from-port="0" to-layer="33" to-port="8" />
649
+ <edge from-layer="32" from-port="0" to-layer="33" to-port="9" />
650
+ <edge from-layer="33" from-port="11" to-layer="34" to-port="0" />
651
+ <edge from-layer="33" from-port="10" to-layer="34" to-port="1" />
652
+ <edge from-layer="33" from-port="10" to-layer="38" to-port="0" />
653
+ <edge from-layer="33" from-port="11" to-layer="38" to-port="1" />
654
+ <edge from-layer="33" from-port="12" to-layer="38" to-port="2" />
655
+ <edge from-layer="34" from-port="2" to-layer="36" to-port="0" />
656
+ <edge from-layer="35" from-port="0" to-layer="36" to-port="1" />
657
+ <edge from-layer="36" from-port="2" to-layer="38" to-port="3" />
658
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="4" />
659
+ <edge from-layer="38" from-port="6" to-layer="39" to-port="0" />
660
+ <edge from-layer="38" from-port="5" to-layer="42" to-port="0" />
661
+ <edge from-layer="39" from-port="1" to-layer="40" to-port="0" />
662
+ <edge from-layer="40" from-port="1" to-layer="41" to-port="0" />
663
+ <edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
664
+ </edges>
665
+ <rt_info>
666
+ <eos_token_id value="2" />
667
+ </rt_info>
668
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff