Hugging Face's logo

EmbeddedLLM
/
bge-m3-int4-ov

OpenVINO
xlm-roberta
Model card Files
xet
 Community
1
tjellm commited on
Commit
2328f52
·
verified ·
1 Parent(s): 7b3c1f7

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +29 -0
  3. openvino_detokenizer.bin +3 -0
  4. openvino_detokenizer.xml +153 -0
  5. openvino_model.bin +3 -0
  6. openvino_model.xml +0 -0
  7. openvino_tokenizer.bin +3 -0
  8. openvino_tokenizer.xml +235 -0
  9. sentencepiece.bpe.model +3 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +55 -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
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/sdp/models/models--BAAI--bge-m3/snapshots/5617a9f61b028005a4858fdac845db406aefb181",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "export_model_type": "transformer",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 8194,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.43.4",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d9c72b4fd3ba3c83bb35f22139463e4ab99b47fae7ae3ac8187243dd58d277
3
+ size 5069133
openvino_detokenizer.xml ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_19724" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_19724">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Constant_19704" type="Const" version="opset1">
14
+ <data element_type="u8" shape="5069084" offset="0" size="5069084" />
15
+ <output>
16
+ <port id="0" precision="U8">
17
+ <dim>5069084</dim>
18
+ </port>
19
+ </output>
20
+ </layer>
21
+ <layer id="2" name="Convert_19739" type="Convert" version="opset1">
22
+ <data destination_type="i32" />
23
+ <input>
24
+ <port id="0" precision="I64">
25
+ <dim>-1</dim>
26
+ <dim>-1</dim>
27
+ </port>
28
+ </input>
29
+ <output>
30
+ <port id="1" precision="I32">
31
+ <dim>-1</dim>
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="SentencepieceDetokenizer_19725" type="SentencepieceDetokenizer" version="extension">
37
+ <input>
38
+ <port id="0" precision="U8">
39
+ <dim>5069084</dim>
40
+ </port>
41
+ <port id="1" precision="I32">
42
+ <dim>-1</dim>
43
+ <dim>-1</dim>
44
+ </port>
45
+ </input>
46
+ <output>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="I32">
51
+ <dim>-1</dim>
52
+ </port>
53
+ <port id="4" precision="U8">
54
+ <dim>-1</dim>
55
+ </port>
56
+ </output>
57
+ </layer>
58
+ <layer id="4" name="Constant_19727" type="Const" version="opset1">
59
+ <data element_type="u8" shape="47" offset="5069084" size="47" />
60
+ <output>
61
+ <port id="0" precision="U8">
62
+ <dim>47</dim>
63
+ </port>
64
+ </output>
65
+ </layer>
66
+ <layer id="5" name="Constant_19729" type="Const" version="opset1">
67
+ <data element_type="u8" shape="2" offset="5069131" size="2" />
68
+ <output>
69
+ <port id="0" precision="U8">
70
+ <dim>2</dim>
71
+ </port>
72
+ </output>
73
+ </layer>
74
+ <layer id="6" name="RegexNormalization_19730" type="RegexNormalization" version="extension">
75
+ <data global_replace="true" />
76
+ <input>
77
+ <port id="0" precision="I32">
78
+ <dim>-1</dim>
79
+ </port>
80
+ <port id="1" precision="I32">
81
+ <dim>-1</dim>
82
+ </port>
83
+ <port id="2" precision="U8">
84
+ <dim>-1</dim>
85
+ </port>
86
+ <port id="3" precision="U8">
87
+ <dim>47</dim>
88
+ </port>
89
+ <port id="4" precision="U8">
90
+ <dim>2</dim>
91
+ </port>
92
+ </input>
93
+ <output>
94
+ <port id="5" precision="I32">
95
+ <dim>-1</dim>
96
+ </port>
97
+ <port id="6" precision="I32">
98
+ <dim>-1</dim>
99
+ </port>
100
+ <port id="7" precision="U8">
101
+ <dim>-1</dim>
102
+ </port>
103
+ </output>
104
+ </layer>
105
+ <layer id="7" name="StringTensorPack_19731" type="StringTensorPack" version="extension">
106
+ <data mode="begins_ends" />
107
+ <input>
108
+ <port id="0" precision="I32">
109
+ <dim>-1</dim>
110
+ </port>
111
+ <port id="1" precision="I32">
112
+ <dim>-1</dim>
113
+ </port>
114
+ <port id="2" precision="U8">
115
+ <dim>-1</dim>
116
+ </port>
117
+ </input>
118
+ <output>
119
+ <port id="3" precision="STRING" names="string_output">
120
+ <dim>-1</dim>
121
+ </port>
122
+ </output>
123
+ </layer>
124
+ <layer id="8" name="Result_19732" type="Result" version="opset1">
125
+ <input>
126
+ <port id="0" precision="STRING">
127
+ <dim>-1</dim>
128
+ </port>
129
+ </input>
130
+ </layer>
131
+ </layers>
132
+ <edges>
133
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
134
+ <edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
135
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
136
+ <edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
137
+ <edge from-layer="3" from-port="3" to-layer="6" to-port="1" />
138
+ <edge from-layer="3" from-port="4" to-layer="6" to-port="2" />
139
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
140
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
141
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
142
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
143
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
144
+ <edge from-layer="7" from-port="3" to-layer="8" to-port="0" />
145
+ </edges>
146
+ <rt_info>
147
+ <bos_token_id value="0" />
148
+ <chat_template value="{% for message in messages %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
149
+ <eos_token_id value="2" />
150
+ <original_tokenizer_class value="&lt;class 'transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast'>" />
151
+ <pad_token_id value="1" />
152
+ </rt_info>
153
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1134182103fd6664946e604e2d12a99a67c5462d03dddee10b2a11d0bc617770
3
+ size 425431703
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:e21a141fddc45a135d71b33803d54b75a9002988ff7dbbfef4fc230d3f781f7d
3
+ size 5069088
openvino_tokenizer.xml ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="string_input" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="string_input">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_19707" 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_19703" type="Const" version="opset1">
19
+ <data element_type="u8" shape="5069080" offset="4" size="5069080" />
20
+ <output>
21
+ <port id="0" precision="U8">
22
+ <dim>5069080</dim>
23
+ </port>
24
+ </output>
25
+ </layer>
26
+ <layer id="3" name="SentencepieceTokenizer_19706" type="SentencepieceTokenizer" version="extension">
27
+ <data nbest_size="0" alpha="0" add_bos="true" add_eos="true" reverse="false" />
28
+ <input>
29
+ <port id="0" precision="U8">
30
+ <dim>5069080</dim>
31
+ </port>
32
+ <port id="1" precision="STRING">
33
+ <dim>-1</dim>
34
+ </port>
35
+ </input>
36
+ <output>
37
+ <port id="2" precision="I64">
38
+ <dim>-1</dim>
39
+ <dim>2</dim>
40
+ </port>
41
+ <port id="3" precision="I32">
42
+ <dim>-1</dim>
43
+ </port>
44
+ <port id="4" precision="I64">
45
+ <dim>2</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Broadcast_19708" type="Broadcast" version="opset3">
50
+ <data mode="numpy" />
51
+ <input>
52
+ <port id="0" precision="I32" />
53
+ <port id="1" precision="I64">
54
+ <dim>2</dim>
55
+ </port>
56
+ </input>
57
+ <output>
58
+ <port id="2" precision="I32">
59
+ <dim>-1</dim>
60
+ <dim>-1</dim>
61
+ </port>
62
+ </output>
63
+ </layer>
64
+ <layer id="5" name="Constant_19709" type="Const" version="opset1">
65
+ <data element_type="i32" shape="" offset="5069084" size="4" />
66
+ <output>
67
+ <port id="0" precision="I32" />
68
+ </output>
69
+ </layer>
70
+ <layer id="6" name="ShapeOf_19710" type="ShapeOf" version="opset3">
71
+ <data output_type="i64" />
72
+ <input>
73
+ <port id="0" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ </input>
77
+ <output>
78
+ <port id="1" precision="I64">
79
+ <dim>1</dim>
80
+ </port>
81
+ </output>
82
+ </layer>
83
+ <layer id="7" name="Broadcast_19711" type="Broadcast" version="opset3">
84
+ <data mode="numpy" />
85
+ <input>
86
+ <port id="0" precision="I32" />
87
+ <port id="1" precision="I64">
88
+ <dim>1</dim>
89
+ </port>
90
+ </input>
91
+ <output>
92
+ <port id="2" precision="I32">
93
+ <dim>-1</dim>
94
+ </port>
95
+ </output>
96
+ </layer>
97
+ <layer id="8" name="ScatterNDUpdate_19715" type="ScatterNDUpdate" version="opset4">
98
+ <input>
99
+ <port id="0" precision="I32">
100
+ <dim>-1</dim>
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I64">
104
+ <dim>-1</dim>
105
+ <dim>2</dim>
106
+ </port>
107
+ <port id="2" precision="I32">
108
+ <dim>-1</dim>
109
+ </port>
110
+ </input>
111
+ <output>
112
+ <port id="3" precision="I32">
113
+ <dim>-1</dim>
114
+ <dim>-1</dim>
115
+ </port>
116
+ </output>
117
+ </layer>
118
+ <layer id="9" name="ScatterNDUpdate_19715" type="Convert" version="opset1">
119
+ <data destination_type="i64" />
120
+ <input>
121
+ <port id="0" precision="I32">
122
+ <dim>-1</dim>
123
+ <dim>-1</dim>
124
+ </port>
125
+ </input>
126
+ <output>
127
+ <port id="1" precision="I64" names="attention_mask">
128
+ <dim>-1</dim>
129
+ <dim>-1</dim>
130
+ </port>
131
+ </output>
132
+ </layer>
133
+ <layer id="11" name="Constant_19716" type="Const" version="opset1">
134
+ <data element_type="i32" shape="" offset="5069084" size="4" />
135
+ <output>
136
+ <port id="0" precision="I32" />
137
+ </output>
138
+ </layer>
139
+ <layer id="12" name="Broadcast_19717" type="Broadcast" version="opset3">
140
+ <data mode="bidirectional" />
141
+ <input>
142
+ <port id="0" precision="I32" />
143
+ <port id="1" precision="I64">
144
+ <dim>2</dim>
145
+ </port>
146
+ </input>
147
+ <output>
148
+ <port id="2" precision="I32">
149
+ <dim>-1</dim>
150
+ <dim>-1</dim>
151
+ </port>
152
+ </output>
153
+ </layer>
154
+ <layer id="13" name="ScatterNDUpdate_19718" type="ScatterNDUpdate" version="opset4">
155
+ <input>
156
+ <port id="0" precision="I32">
157
+ <dim>-1</dim>
158
+ <dim>-1</dim>
159
+ </port>
160
+ <port id="1" precision="I64">
161
+ <dim>-1</dim>
162
+ <dim>2</dim>
163
+ </port>
164
+ <port id="2" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ </input>
168
+ <output>
169
+ <port id="3" precision="I32">
170
+ <dim>-1</dim>
171
+ <dim>-1</dim>
172
+ </port>
173
+ </output>
174
+ </layer>
175
+ <layer id="14" name="ScatterNDUpdate_19718" type="Convert" version="opset1">
176
+ <data destination_type="i64" />
177
+ <input>
178
+ <port id="0" precision="I32">
179
+ <dim>-1</dim>
180
+ <dim>-1</dim>
181
+ </port>
182
+ </input>
183
+ <output>
184
+ <port id="1" precision="I64" names="input_ids">
185
+ <dim>-1</dim>
186
+ <dim>-1</dim>
187
+ </port>
188
+ </output>
189
+ </layer>
190
+ <layer id="15" name="Result_19719" type="Result" version="opset1">
191
+ <input>
192
+ <port id="0" precision="I64">
193
+ <dim>-1</dim>
194
+ <dim>-1</dim>
195
+ </port>
196
+ </input>
197
+ </layer>
198
+ <layer id="10" name="Result_19720" type="Result" version="opset1">
199
+ <input>
200
+ <port id="0" precision="I64">
201
+ <dim>-1</dim>
202
+ <dim>-1</dim>
203
+ </port>
204
+ </input>
205
+ </layer>
206
+ </layers>
207
+ <edges>
208
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
209
+ <edge from-layer="1" from-port="0" to-layer="4" to-port="0" />
210
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
211
+ <edge from-layer="3" from-port="4" to-layer="4" to-port="1" />
212
+ <edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
213
+ <edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
214
+ <edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
215
+ <edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
216
+ <edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
217
+ <edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
218
+ <edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
219
+ <edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
220
+ <edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
221
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
222
+ <edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
223
+ <edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
224
+ <edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
225
+ <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
226
+ <edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
227
+ </edges>
228
+ <rt_info>
229
+ <bos_token_id value="0" />
230
+ <chat_template value="{% for message in messages %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
231
+ <eos_token_id value="2" />
232
+ <original_tokenizer_class value="&lt;class 'transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast'>" />
233
+ <pad_token_id value="1" />
234
+ </rt_info>
235
+ </net>
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249df0778f236f6ece390de0de746838ef25b9d6954b68c2ee71249e0a9d8fd4
3
+ size 17082799
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 8192,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }