Hugging Face's logo

Monimoy
/
openvino_phi2

OpenVINO
phi
Model card Files
xet
Community
Monimoy commited on
Commit
79d9b5b
·
verified ·
1 Parent(s): c96ad31

Openvino phi2 model

Browse files
Files changed (14) hide show
  1. added_tokens.json +40 -0
  2. config.json +31 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. openvino_detokenizer.bin +3 -0
  6. openvino_detokenizer.xml +270 -0
  7. openvino_model.bin +3 -0
  8. openvino_model.xml +0 -0
  9. openvino_tokenizer.bin +3 -0
  10. openvino_tokenizer.xml +684 -0
  11. special_tokens_map.json +23 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +325 -0
  14. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "microsoft/phi-2",
4
+ "architectures": [
5
+ "PhiForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "hidden_act": "gelu_new",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 10240,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "phi",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "partial_rotary_factor": 0.4,
22
+ "qk_layernorm": false,
23
+ "resid_pdrop": 0.1,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.49.0",
29
+ "use_cache": true,
30
+ "vocab_size": 51200
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.49.0"
6
+ }
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 sha256:15afc78c7aae435111a03b20bf79399123e381900789d0d028d2e0524deda0f0
3
+ size 723783
openvino_detokenizer.xml ADDED
@@ -0,0 +1,270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_56916" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_56916">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_57008" 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_56918" type="Const" version="opset1">
29
+ <data element_type="i32" shape="50295" offset="0" size="201180" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>50295</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_56920" type="Const" version="opset1">
37
+ <data element_type="i32" shape="50295" offset="201180" size="201180" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>50295</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_56922" type="Const" version="opset1">
45
+ <data element_type="u8" shape="321366" offset="402360" size="321366" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>321366</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_56927" type="Const" version="opset1">
53
+ <data element_type="i32" shape="1" offset="723726" size="4" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>1</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_56929" type="VocabDecoder" version="extension">
61
+ <data skip_tokens="" />
62
+ <input>
63
+ <port id="0" precision="I32">
64
+ <dim>-1</dim>
65
+ <dim>-1</dim>
66
+ </port>
67
+ <port id="1" precision="I32">
68
+ <dim>50295</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>50295</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>321366</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>1</dim>
78
+ </port>
79
+ </input>
80
+ <output>
81
+ <port id="5" precision="I32">
82
+ <dim>-1</dim>
83
+ </port>
84
+ <port id="6" precision="I32">
85
+ <dim>-1</dim>
86
+ </port>
87
+ <port id="7" precision="I32">
88
+ <dim>-1</dim>
89
+ </port>
90
+ <port id="8" precision="I32">
91
+ <dim>-1</dim>
92
+ </port>
93
+ <port id="9" precision="U8">
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="FuzeRagged_56930" type="FuzeRagged" version="extension">
99
+ <input>
100
+ <port id="0" precision="I32">
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I32">
104
+ <dim>-1</dim>
105
+ </port>
106
+ <port id="2" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="4" precision="I32">
115
+ <dim>-1</dim>
116
+ </port>
117
+ <port id="5" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="8" name="UTF8Validate_56931" type="UTF8Validate" version="extension">
123
+ <data replace_mode="true" />
124
+ <input>
125
+ <port id="0" precision="I32">
126
+ <dim>-1</dim>
127
+ </port>
128
+ <port id="1" precision="I32">
129
+ <dim>-1</dim>
130
+ </port>
131
+ <port id="2" precision="U8">
132
+ <dim>-1</dim>
133
+ </port>
134
+ </input>
135
+ <output>
136
+ <port id="3" precision="I32">
137
+ <dim>-1</dim>
138
+ </port>
139
+ <port id="4" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="5" precision="U8">
143
+ <dim>-1</dim>
144
+ </port>
145
+ </output>
146
+ </layer>
147
+ <layer id="9" name="Constant_56933" type="Const" version="opset1">
148
+ <data element_type="u8" shape="51" offset="723730" size="51" />
149
+ <output>
150
+ <port id="0" precision="U8">
151
+ <dim>51</dim>
152
+ </port>
153
+ </output>
154
+ </layer>
155
+ <layer id="10" name="Constant_56935" type="Const" version="opset1">
156
+ <data element_type="u8" shape="2" offset="723781" size="2" />
157
+ <output>
158
+ <port id="0" precision="U8">
159
+ <dim>2</dim>
160
+ </port>
161
+ </output>
162
+ </layer>
163
+ <layer id="11" name="RegexNormalization_56936" type="RegexNormalization" version="extension">
164
+ <data global_replace="true" />
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="U8">
173
+ <dim>-1</dim>
174
+ </port>
175
+ <port id="3" precision="U8">
176
+ <dim>51</dim>
177
+ </port>
178
+ <port id="4" precision="U8">
179
+ <dim>2</dim>
180
+ </port>
181
+ </input>
182
+ <output>
183
+ <port id="5" precision="I32">
184
+ <dim>-1</dim>
185
+ </port>
186
+ <port id="6" precision="I32">
187
+ <dim>-1</dim>
188
+ </port>
189
+ <port id="7" precision="U8">
190
+ <dim>-1</dim>
191
+ </port>
192
+ </output>
193
+ </layer>
194
+ <layer id="12" name="StringTensorPack_56937" type="StringTensorPack" version="opset15">
195
+ <input>
196
+ <port id="0" precision="I32">
197
+ <dim>-1</dim>
198
+ </port>
199
+ <port id="1" precision="I32">
200
+ <dim>-1</dim>
201
+ </port>
202
+ <port id="2" precision="U8">
203
+ <dim>-1</dim>
204
+ </port>
205
+ </input>
206
+ <output>
207
+ <port id="3" precision="STRING" names="Result_56938,string_output">
208
+ <dim>-1</dim>
209
+ </port>
210
+ </output>
211
+ </layer>
212
+ <layer id="13" name="Result_56938" type="Result" version="opset1" output_names="Result_56938,string_output">
213
+ <input>
214
+ <port id="0" precision="STRING">
215
+ <dim>-1</dim>
216
+ </port>
217
+ </input>
218
+ </layer>
219
+ </layers>
220
+ <edges>
221
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
222
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
223
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
224
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
225
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
226
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
227
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
228
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
229
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
230
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
231
+ <edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
232
+ <edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
233
+ <edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
234
+ <edge from-layer="8" from-port="3" to-layer="11" to-port="0" />
235
+ <edge from-layer="8" from-port="4" to-layer="11" to-port="1" />
236
+ <edge from-layer="8" from-port="5" to-layer="11" to-port="2" />
237
+ <edge from-layer="9" from-port="0" to-layer="11" to-port="3" />
238
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="4" />
239
+ <edge from-layer="11" from-port="5" to-layer="12" to-port="0" />
240
+ <edge from-layer="11" from-port="6" to-layer="12" to-port="1" />
241
+ <edge from-layer="11" from-port="7" to-layer="12" to-port="2" />
242
+ <edge from-layer="12" from-port="3" to-layer="13" to-port="0" />
243
+ </edges>
244
+ <rt_info>
245
+ <add_attention_mask value="True" />
246
+ <add_prefix_space />
247
+ <add_special_tokens value="True" />
248
+ <bos_token_id value="50256" />
249
+ <clean_up_tokenization_spaces />
250
+ <detokenizer_input_type value="i64" />
251
+ <eos_token_id value="50256" />
252
+ <handle_special_tokens_with_re />
253
+ <max_length />
254
+ <number_of_inputs value="1" />
255
+ <openvino_tokenizers_version value="2025.1.0.0-514-26d9676e93f" />
256
+ <openvino_version value="2025.1.0-18391-ed8e7bd23f1" />
257
+ <original_tokenizer_class value="&lt;class 'transformers.models.codegen.tokenization_codegen_fast.CodeGenTokenizerFast'>" />
258
+ <sentencepiece_version value="0.2.0" />
259
+ <skip_special_tokens value="True" />
260
+ <streaming_detokenizer value="False" />
261
+ <tiktoken_version value="0.9.0" />
262
+ <tokenizer_output_type value="i64" />
263
+ <tokenizers_version value="0.21.0" />
264
+ <transformers_version value="4.49.0" />
265
+ <use_max_padding value="False" />
266
+ <use_sentencepiece_backend value="False" />
267
+ <utf8_replace_mode value="replace" />
268
+ <with_detokenizer value="True" />
269
+ </rt_info>
270
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bc3531015ff15dc52cb938bd6ebcf89f7ae58b04da08435cb26e84a8df312d
3
+ size 1621299520
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 sha256:8778c6db77325a73635987342a9d815ad36985db3cef3e89c4b0e98ff89ef2b3
3
+ size 1846613
openvino_tokenizer.xml ADDED
@@ -0,0 +1,684 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_56798" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_56798">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_56804" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_56799" type="StringTensorUnpack" version="opset15">
19
+ <input>
20
+ <port id="0" precision="STRING">
21
+ <dim>-1</dim>
22
+ </port>
23
+ </input>
24
+ <output>
25
+ <port id="1" precision="I32">
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="2" precision="I32">
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="3" precision="U8">
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="ShapeOf_56800" type="ShapeOf" version="opset3">
37
+ <data output_type="i64" />
38
+ <input>
39
+ <port id="0" precision="I32">
40
+ <dim>-1</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I64">
45
+ <dim>1</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Constant_56801" type="Const" version="opset1">
50
+ <data element_type="i64" shape="" offset="0" size="8" />
51
+ <output>
52
+ <port id="0" precision="I64" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_56802" type="Const" version="opset1">
56
+ <data element_type="i64" shape="" offset="0" size="8" />
57
+ <output>
58
+ <port id="0" precision="I64" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_56803" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ <port id="1" precision="I64" />
68
+ <port id="2" precision="I64" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_56805" type="Const" version="opset1">
75
+ <data element_type="i64" shape="" offset="8" size="8" />
76
+ <output>
77
+ <port id="0" precision="I64" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_56806" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I64" />
86
+ </input>
87
+ <output>
88
+ <port id="3" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ </output>
92
+ </layer>
93
+ <layer id="9" name="Constant_56807" type="Const" version="opset1">
94
+ <data element_type="i64" shape="" offset="8" size="8" />
95
+ <output>
96
+ <port id="0" precision="I64" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_56808" type="Const" version="opset1">
100
+ <data element_type="i64" shape="" offset="8" size="8" />
101
+ <output>
102
+ <port id="0" precision="I64" />
103
+ </output>
104
+ </layer>
105
+ <layer id="11" name="Add_56809" type="Add" version="opset1">
106
+ <data auto_broadcast="numpy" />
107
+ <input>
108
+ <port id="0" precision="I64" />
109
+ <port id="1" precision="I64" />
110
+ </input>
111
+ <output>
112
+ <port id="2" precision="I64" />
113
+ </output>
114
+ </layer>
115
+ <layer id="12" name="Constant_56810" type="Const" version="opset1">
116
+ <data element_type="i64" shape="" offset="8" size="8" />
117
+ <output>
118
+ <port id="0" precision="I64" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_56811" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I64" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I64" />
127
+ </input>
128
+ <output>
129
+ <port id="3" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="14" name="Constant_56873" type="Const" version="opset1">
135
+ <data element_type="u8" shape="1211" offset="16" size="1211" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>1211</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_56874" type="SpecialTokensSplit" version="extension">
143
+ <input>
144
+ <port id="0" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="1" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="2" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="3" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="4" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="5" precision="U8">
160
+ <dim>1211</dim>
161
+ </port>
162
+ </input>
163
+ <output>
164
+ <port id="6" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="7" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="8" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="9" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="10" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="11" precision="BOOL">
180
+ <dim>-1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="16" name="Constant_56876" type="Const" version="opset1">
185
+ <data element_type="u8" shape="74" offset="1227" size="74" />
186
+ <output>
187
+ <port id="0" precision="U8">
188
+ <dim>74</dim>
189
+ </port>
190
+ </output>
191
+ </layer>
192
+ <layer id="17" name="RegexSplit_56877" type="RegexSplit" version="extension">
193
+ <data behaviour="isolate" invert="false" max_splits="-1" />
194
+ <input>
195
+ <port id="0" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="1" precision="I32">
199
+ <dim>-1</dim>
200
+ </port>
201
+ <port id="2" precision="I32">
202
+ <dim>-1</dim>
203
+ </port>
204
+ <port id="3" precision="I32">
205
+ <dim>-1</dim>
206
+ </port>
207
+ <port id="4" precision="U8">
208
+ <dim>-1</dim>
209
+ </port>
210
+ <port id="5" precision="BOOL">
211
+ <dim>-1</dim>
212
+ </port>
213
+ <port id="6" precision="U8">
214
+ <dim>74</dim>
215
+ </port>
216
+ </input>
217
+ <output>
218
+ <port id="7" precision="I32">
219
+ <dim>-1</dim>
220
+ </port>
221
+ <port id="8" precision="I32">
222
+ <dim>-1</dim>
223
+ </port>
224
+ <port id="9" precision="I32">
225
+ <dim>-1</dim>
226
+ </port>
227
+ <port id="10" precision="I32">
228
+ <dim>-1</dim>
229
+ </port>
230
+ <port id="11" precision="U8">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="12" precision="BOOL">
234
+ <dim>-1</dim>
235
+ </port>
236
+ </output>
237
+ </layer>
238
+ <layer id="18" name="Constant_56879" type="Const" version="opset1">
239
+ <data element_type="i32" shape="50295" offset="1301" size="201180" />
240
+ <output>
241
+ <port id="0" precision="I32">
242
+ <dim>50295</dim>
243
+ </port>
244
+ </output>
245
+ </layer>
246
+ <layer id="19" name="Constant_56881" type="Const" version="opset1">
247
+ <data element_type="i32" shape="50295" offset="202481" size="201180" />
248
+ <output>
249
+ <port id="0" precision="I32">
250
+ <dim>50295</dim>
251
+ </port>
252
+ </output>
253
+ </layer>
254
+ <layer id="20" name="Constant_56883" type="Const" version="opset1">
255
+ <data element_type="u8" shape="321366" offset="403661" size="321366" />
256
+ <output>
257
+ <port id="0" precision="U8">
258
+ <dim>321366</dim>
259
+ </port>
260
+ </output>
261
+ </layer>
262
+ <layer id="21" name="Constant_56891" type="Const" version="opset1">
263
+ <data element_type="i32" shape="50000" offset="725027" size="200000" />
264
+ <output>
265
+ <port id="0" precision="I32">
266
+ <dim>50000</dim>
267
+ </port>
268
+ </output>
269
+ </layer>
270
+ <layer id="22" name="Constant_56893" type="Const" version="opset1">
271
+ <data element_type="i32" shape="50000" offset="925027" size="200000" />
272
+ <output>
273
+ <port id="0" precision="I32">
274
+ <dim>50000</dim>
275
+ </port>
276
+ </output>
277
+ </layer>
278
+ <layer id="23" name="Constant_56895" type="Const" version="opset1">
279
+ <data element_type="u8" shape="167515" offset="1125027" size="167515" />
280
+ <output>
281
+ <port id="0" precision="U8">
282
+ <dim>167515</dim>
283
+ </port>
284
+ </output>
285
+ </layer>
286
+ <layer id="24" name="Constant_56897" type="Const" version="opset1">
287
+ <data element_type="i32" shape="50000" offset="1292542" size="200000" />
288
+ <output>
289
+ <port id="0" precision="I32">
290
+ <dim>50000</dim>
291
+ </port>
292
+ </output>
293
+ </layer>
294
+ <layer id="25" name="Constant_56899" type="Const" version="opset1">
295
+ <data element_type="i32" shape="50000" offset="1492542" size="200000" />
296
+ <output>
297
+ <port id="0" precision="I32">
298
+ <dim>50000</dim>
299
+ </port>
300
+ </output>
301
+ </layer>
302
+ <layer id="26" name="Constant_56901" type="Const" version="opset1">
303
+ <data element_type="u8" shape="153043" offset="1692542" size="153043" />
304
+ <output>
305
+ <port id="0" precision="U8">
306
+ <dim>153043</dim>
307
+ </port>
308
+ </output>
309
+ </layer>
310
+ <layer id="27" name="Constant_56885" type="Const" version="opset1">
311
+ <data element_type="i32" shape="39" offset="1845585" size="156" />
312
+ <output>
313
+ <port id="0" precision="I32">
314
+ <dim>39</dim>
315
+ </port>
316
+ </output>
317
+ </layer>
318
+ <layer id="28" name="Constant_56887" type="Const" version="opset1">
319
+ <data element_type="i32" shape="39" offset="1845741" size="156" />
320
+ <output>
321
+ <port id="0" precision="I32">
322
+ <dim>39</dim>
323
+ </port>
324
+ </output>
325
+ </layer>
326
+ <layer id="29" name="Constant_56889" type="Const" version="opset1">
327
+ <data element_type="u8" shape="552" offset="1845897" size="552" />
328
+ <output>
329
+ <port id="0" precision="U8">
330
+ <dim>552</dim>
331
+ </port>
332
+ </output>
333
+ </layer>
334
+ <layer id="30" name="Constant_56902" type="Const" version="opset1">
335
+ <data element_type="i32" shape="39" offset="1846449" size="156" />
336
+ <output>
337
+ <port id="0" precision="I32">
338
+ <dim>39</dim>
339
+ </port>
340
+ </output>
341
+ </layer>
342
+ <layer id="31" name="BPETokenizer_56903" type="BPETokenizer" version="extension">
343
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="20000" />
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
+ <port id="2" precision="I32">
352
+ <dim>-1</dim>
353
+ </port>
354
+ <port id="3" precision="I32">
355
+ <dim>-1</dim>
356
+ </port>
357
+ <port id="4" precision="U8">
358
+ <dim>-1</dim>
359
+ </port>
360
+ <port id="5" precision="I32">
361
+ <dim>50295</dim>
362
+ </port>
363
+ <port id="6" precision="I32">
364
+ <dim>50295</dim>
365
+ </port>
366
+ <port id="7" precision="U8">
367
+ <dim>321366</dim>
368
+ </port>
369
+ <port id="8" precision="I32">
370
+ <dim>50000</dim>
371
+ </port>
372
+ <port id="9" precision="I32">
373
+ <dim>50000</dim>
374
+ </port>
375
+ <port id="10" precision="U8">
376
+ <dim>167515</dim>
377
+ </port>
378
+ <port id="11" precision="I32">
379
+ <dim>50000</dim>
380
+ </port>
381
+ <port id="12" precision="I32">
382
+ <dim>50000</dim>
383
+ </port>
384
+ <port id="13" precision="U8">
385
+ <dim>153043</dim>
386
+ </port>
387
+ <port id="14" precision="I32">
388
+ <dim>39</dim>
389
+ </port>
390
+ <port id="15" precision="I32">
391
+ <dim>39</dim>
392
+ </port>
393
+ <port id="16" precision="U8">
394
+ <dim>552</dim>
395
+ </port>
396
+ <port id="17" precision="I32">
397
+ <dim>39</dim>
398
+ </port>
399
+ </input>
400
+ <output>
401
+ <port id="18" precision="I32">
402
+ <dim>-1</dim>
403
+ </port>
404
+ <port id="19" precision="I32">
405
+ <dim>-1</dim>
406
+ </port>
407
+ <port id="20" precision="I32">
408
+ <dim>-1</dim>
409
+ </port>
410
+ </output>
411
+ </layer>
412
+ <layer id="32" name="Subtract_56904" type="Subtract" version="opset1">
413
+ <data auto_broadcast="numpy" />
414
+ <input>
415
+ <port id="0" precision="I32">
416
+ <dim>-1</dim>
417
+ </port>
418
+ <port id="1" precision="I32">
419
+ <dim>-1</dim>
420
+ </port>
421
+ </input>
422
+ <output>
423
+ <port id="2" precision="I32">
424
+ <dim>-1</dim>
425
+ </port>
426
+ </output>
427
+ </layer>
428
+ <layer id="33" name="Constant_56905" type="Const" version="opset1">
429
+ <data element_type="i32" shape="" offset="1846605" size="4" />
430
+ <output>
431
+ <port id="0" precision="I32" />
432
+ </output>
433
+ </layer>
434
+ <layer id="34" name="Minimum_56906" type="Minimum" version="opset1">
435
+ <data auto_broadcast="numpy" />
436
+ <input>
437
+ <port id="0" precision="I32">
438
+ <dim>-1</dim>
439
+ </port>
440
+ <port id="1" precision="I32" />
441
+ </input>
442
+ <output>
443
+ <port id="2" precision="I32">
444
+ <dim>-1</dim>
445
+ </port>
446
+ </output>
447
+ </layer>
448
+ <layer id="35" name="Subtract_56907" type="Subtract" version="opset1">
449
+ <data auto_broadcast="numpy" />
450
+ <input>
451
+ <port id="0" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ <port id="1" precision="I32">
455
+ <dim>-1</dim>
456
+ </port>
457
+ </input>
458
+ <output>
459
+ <port id="2" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ </output>
463
+ </layer>
464
+ <layer id="36" name="Subtract_56908" type="Subtract" version="opset1">
465
+ <data auto_broadcast="numpy" />
466
+ <input>
467
+ <port id="0" precision="I32">
468
+ <dim>-1</dim>
469
+ </port>
470
+ <port id="1" precision="I32">
471
+ <dim>-1</dim>
472
+ </port>
473
+ </input>
474
+ <output>
475
+ <port id="2" precision="I32">
476
+ <dim>-1</dim>
477
+ </port>
478
+ </output>
479
+ </layer>
480
+ <layer id="37" name="Constant_56909" type="Const" version="opset1">
481
+ <data element_type="i32" shape="" offset="1846609" size="4" />
482
+ <output>
483
+ <port id="0" precision="I32" />
484
+ </output>
485
+ </layer>
486
+ <layer id="38" name="ReduceMax_56910" type="ReduceMax" version="opset1">
487
+ <data keep_dims="false" />
488
+ <input>
489
+ <port id="0" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="1" precision="I32" />
493
+ </input>
494
+ <output>
495
+ <port id="2" precision="I32" />
496
+ </output>
497
+ </layer>
498
+ <layer id="39" name="Constant_56911" type="Const" version="opset1">
499
+ <data element_type="i32" shape="" offset="1846609" size="4" />
500
+ <output>
501
+ <port id="0" precision="I32" />
502
+ </output>
503
+ </layer>
504
+ <layer id="40" name="RaggedToDense_56912" type="RaggedToDense" version="extension">
505
+ <data pad_right="false" m_pad_max_length="false" />
506
+ <input>
507
+ <port id="0" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ <port id="1" precision="I32">
511
+ <dim>-1</dim>
512
+ </port>
513
+ <port id="2" precision="I32">
514
+ <dim>-1</dim>
515
+ </port>
516
+ <port id="3" precision="I32" />
517
+ <port id="4" precision="I32" />
518
+ </input>
519
+ <output>
520
+ <port id="5" precision="I32">
521
+ <dim>-1</dim>
522
+ <dim>-1</dim>
523
+ </port>
524
+ <port id="6" precision="BOOL">
525
+ <dim>-1</dim>
526
+ <dim>-1</dim>
527
+ </port>
528
+ </output>
529
+ </layer>
530
+ <layer id="41" name="Convert_56913" type="Convert" version="opset1">
531
+ <data destination_type="i32" />
532
+ <input>
533
+ <port id="0" precision="BOOL">
534
+ <dim>-1</dim>
535
+ <dim>-1</dim>
536
+ </port>
537
+ </input>
538
+ <output>
539
+ <port id="1" precision="I32">
540
+ <dim>-1</dim>
541
+ <dim>-1</dim>
542
+ </port>
543
+ </output>
544
+ </layer>
545
+ <layer id="42" name="Convert_56913.0" type="Convert" version="opset1">
546
+ <data destination_type="i64" />
547
+ <input>
548
+ <port id="0" precision="I32">
549
+ <dim>-1</dim>
550
+ <dim>-1</dim>
551
+ </port>
552
+ </input>
553
+ <output>
554
+ <port id="1" precision="I64" names="attention_mask">
555
+ <dim>-1</dim>
556
+ <dim>-1</dim>
557
+ </port>
558
+ </output>
559
+ </layer>
560
+ <layer id="44" name="RaggedToDense_56912.0" type="Convert" version="opset1">
561
+ <data destination_type="i64" />
562
+ <input>
563
+ <port id="0" precision="I32">
564
+ <dim>-1</dim>
565
+ <dim>-1</dim>
566
+ </port>
567
+ </input>
568
+ <output>
569
+ <port id="1" precision="I64" names="input_ids">
570
+ <dim>-1</dim>
571
+ <dim>-1</dim>
572
+ </port>
573
+ </output>
574
+ </layer>
575
+ <layer id="45" name="Result_56914" type="Result" version="opset1" output_names="input_ids">
576
+ <input>
577
+ <port id="0" precision="I64">
578
+ <dim>-1</dim>
579
+ <dim>-1</dim>
580
+ </port>
581
+ </input>
582
+ </layer>
583
+ <layer id="43" name="Result_56915" type="Result" version="opset1" output_names="attention_mask">
584
+ <input>
585
+ <port id="0" precision="I64">
586
+ <dim>-1</dim>
587
+ <dim>-1</dim>
588
+ </port>
589
+ </input>
590
+ </layer>
591
+ </layers>
592
+ <edges>
593
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
594
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
595
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
596
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
597
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
598
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
599
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
600
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
601
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
602
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
603
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
604
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
605
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
606
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
607
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
608
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
609
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
610
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
611
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
612
+ <edge from-layer="15" from-port="6" to-layer="17" to-port="0" />
613
+ <edge from-layer="15" from-port="7" to-layer="17" to-port="1" />
614
+ <edge from-layer="15" from-port="8" to-layer="17" to-port="2" />
615
+ <edge from-layer="15" from-port="9" to-layer="17" to-port="3" />
616
+ <edge from-layer="15" from-port="10" to-layer="17" to-port="4" />
617
+ <edge from-layer="15" from-port="11" to-layer="17" to-port="5" />
618
+ <edge from-layer="16" from-port="0" to-layer="17" to-port="6" />
619
+ <edge from-layer="17" from-port="7" to-layer="31" to-port="0" />
620
+ <edge from-layer="17" from-port="8" to-layer="31" to-port="1" />
621
+ <edge from-layer="17" from-port="9" to-layer="31" to-port="2" />
622
+ <edge from-layer="17" from-port="10" to-layer="31" to-port="3" />
623
+ <edge from-layer="17" from-port="11" to-layer="31" to-port="4" />
624
+ <edge from-layer="18" from-port="0" to-layer="31" to-port="5" />
625
+ <edge from-layer="19" from-port="0" to-layer="31" to-port="6" />
626
+ <edge from-layer="20" from-port="0" to-layer="31" to-port="7" />
627
+ <edge from-layer="21" from-port="0" to-layer="31" to-port="8" />
628
+ <edge from-layer="22" from-port="0" to-layer="31" to-port="9" />
629
+ <edge from-layer="23" from-port="0" to-layer="31" to-port="10" />
630
+ <edge from-layer="24" from-port="0" to-layer="31" to-port="11" />
631
+ <edge from-layer="25" from-port="0" to-layer="31" to-port="12" />
632
+ <edge from-layer="26" from-port="0" to-layer="31" to-port="13" />
633
+ <edge from-layer="27" from-port="0" to-layer="31" to-port="14" />
634
+ <edge from-layer="28" from-port="0" to-layer="31" to-port="15" />
635
+ <edge from-layer="29" from-port="0" to-layer="31" to-port="16" />
636
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
637
+ <edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
638
+ <edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
639
+ <edge from-layer="31" from-port="19" to-layer="40" to-port="1" />
640
+ <edge from-layer="31" from-port="19" to-layer="35" to-port="0" />
641
+ <edge from-layer="31" from-port="19" to-layer="36" to-port="0" />
642
+ <edge from-layer="31" from-port="20" to-layer="40" to-port="2" />
643
+ <edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
644
+ <edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
645
+ <edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
646
+ <edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
647
+ <edge from-layer="35" from-port="2" to-layer="40" to-port="0" />
648
+ <edge from-layer="36" from-port="2" to-layer="38" to-port="0" />
649
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
650
+ <edge from-layer="38" from-port="2" to-layer="40" to-port="3" />
651
+ <edge from-layer="39" from-port="0" to-layer="40" to-port="4" />
652
+ <edge from-layer="40" from-port="6" to-layer="41" to-port="0" />
653
+ <edge from-layer="40" from-port="5" to-layer="44" to-port="0" />
654
+ <edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
655
+ <edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
656
+ <edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
657
+ </edges>
658
+ <rt_info>
659
+ <add_attention_mask value="True" />
660
+ <add_prefix_space />
661
+ <add_special_tokens value="True" />
662
+ <bos_token_id value="50256" />
663
+ <clean_up_tokenization_spaces />
664
+ <detokenizer_input_type value="i64" />
665
+ <eos_token_id value="50256" />
666
+ <handle_special_tokens_with_re />
667
+ <max_length />
668
+ <number_of_inputs value="1" />
669
+ <openvino_tokenizers_version value="2025.1.0.0-514-26d9676e93f" />
670
+ <openvino_version value="2025.1.0-18391-ed8e7bd23f1" />
671
+ <original_tokenizer_class value="&lt;class 'transformers.models.codegen.tokenization_codegen_fast.CodeGenTokenizerFast'>" />
672
+ <sentencepiece_version value="0.2.0" />
673
+ <skip_special_tokens value="True" />
674
+ <streaming_detokenizer value="False" />
675
+ <tiktoken_version value="0.9.0" />
676
+ <tokenizer_output_type value="i64" />
677
+ <tokenizers_version value="0.21.0" />
678
+ <transformers_version value="4.49.0" />
679
+ <use_max_padding value="False" />
680
+ <use_sentencepiece_backend value="False" />
681
+ <utf8_replace_mode value="replace" />
682
+ <with_detokenizer value="True" />
683
+ </rt_info>
684
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "extra_special_tokens": {},
321
+ "model_max_length": 2048,
322
+ "return_token_type_ids": false,
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff