Hugging Face's logo

OpenVINO
/
Phi-3-mini-FastDraft-50M-int8-ov

OpenVINO
phi3
Model card Files
xet
Community
1
katuni4ka commited on
Commit
7d14c54
·
verified ·
1 Parent(s): 8c7869a

add tokenizer files

Browse files
Files changed (7) hide show
  1. added_tokens.json +13 -0
  2. openvino_detokenizer.bin +3 -0
  3. openvino_detokenizer.xml +295 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +131 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf0a5ac7698c27f1f3a8573b76a628e4a6a2c7eaddc7dd549ee3607a34d4061
3
+ size 339125
openvino_detokenizer.xml ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_282016" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_282016">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_282038" 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_281986" type="Const" version="opset1">
29
+ <data element_type="u8" shape="339118" offset="0" size="339118" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>339118</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_281987" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>339118</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_282017" type="VocabDecoder" version="extension">
56
+ <data skip_tokens="0, 1, 32000, 32001, 32002, 32003, 32004, 32005, 32006, 32007, 32008, 32009, 32010" />
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="Constant_282019" type="Const" version="opset1">
91
+ <data element_type="u8" shape="3" offset="339118" size="3" />
92
+ <output>
93
+ <port id="0" precision="U8">
94
+ <dim>3</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="6" name="Constant_282021" type="Const" version="opset1">
99
+ <data element_type="u8" shape="1" offset="339121" size="1" />
100
+ <output>
101
+ <port id="0" precision="U8">
102
+ <dim>1</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="7" name="RegexNormalization_282022" type="RegexNormalization" version="extension">
107
+ <data global_replace="true" />
108
+ <input>
109
+ <port id="0" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ <port id="1" precision="I32">
113
+ <dim>-1</dim>
114
+ </port>
115
+ <port id="2" precision="U8">
116
+ <dim>-1</dim>
117
+ </port>
118
+ <port id="3" precision="U8">
119
+ <dim>3</dim>
120
+ </port>
121
+ <port id="4" precision="U8">
122
+ <dim>1</dim>
123
+ </port>
124
+ </input>
125
+ <output>
126
+ <port id="5" precision="I32">
127
+ <dim>-1</dim>
128
+ </port>
129
+ <port id="6" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ <port id="7" precision="U8">
133
+ <dim>-1</dim>
134
+ </port>
135
+ </output>
136
+ </layer>
137
+ <layer id="8" name="ByteFallback_282023" type="ByteFallback" version="extension">
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
+ </input>
149
+ <output>
150
+ <port id="3" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="4" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="5" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ </output>
160
+ </layer>
161
+ <layer id="9" name="FuzeRagged_282024" type="FuzeRagged" version="extension">
162
+ <input>
163
+ <port id="0" precision="I32">
164
+ <dim>-1</dim>
165
+ </port>
166
+ <port id="1" precision="I32">
167
+ <dim>-1</dim>
168
+ </port>
169
+ <port id="2" precision="I32">
170
+ <dim>-1</dim>
171
+ </port>
172
+ <port id="3" precision="I32">
173
+ <dim>-1</dim>
174
+ </port>
175
+ </input>
176
+ <output>
177
+ <port id="4" precision="I32">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="5" precision="I32">
181
+ <dim>-1</dim>
182
+ </port>
183
+ </output>
184
+ </layer>
185
+ <layer id="10" name="Constant_282026" type="Const" version="opset1">
186
+ <data element_type="u8" shape="2" offset="339122" size="2" />
187
+ <output>
188
+ <port id="0" precision="U8">
189
+ <dim>2</dim>
190
+ </port>
191
+ </output>
192
+ </layer>
193
+ <layer id="11" name="Constant_282028" type="Const" version="opset1">
194
+ <data element_type="u8" shape="0" offset="339124" size="1" />
195
+ <output>
196
+ <port id="0" precision="U8">
197
+ <dim>0</dim>
198
+ </port>
199
+ </output>
200
+ </layer>
201
+ <layer id="12" name="RegexNormalization_282029" type="RegexNormalization" version="extension">
202
+ <data global_replace="true" />
203
+ <input>
204
+ <port id="0" precision="I32">
205
+ <dim>-1</dim>
206
+ </port>
207
+ <port id="1" precision="I32">
208
+ <dim>-1</dim>
209
+ </port>
210
+ <port id="2" precision="U8">
211
+ <dim>-1</dim>
212
+ </port>
213
+ <port id="3" precision="U8">
214
+ <dim>2</dim>
215
+ </port>
216
+ <port id="4" precision="U8">
217
+ <dim>0</dim>
218
+ </port>
219
+ </input>
220
+ <output>
221
+ <port id="5" precision="I32">
222
+ <dim>-1</dim>
223
+ </port>
224
+ <port id="6" precision="I32">
225
+ <dim>-1</dim>
226
+ </port>
227
+ <port id="7" precision="U8">
228
+ <dim>-1</dim>
229
+ </port>
230
+ </output>
231
+ </layer>
232
+ <layer id="13" name="StringTensorPack_282030" type="StringTensorPack" version="extension">
233
+ <data mode="begins_ends" />
234
+ <input>
235
+ <port id="0" precision="I32">
236
+ <dim>-1</dim>
237
+ </port>
238
+ <port id="1" precision="I32">
239
+ <dim>-1</dim>
240
+ </port>
241
+ <port id="2" precision="U8">
242
+ <dim>-1</dim>
243
+ </port>
244
+ </input>
245
+ <output>
246
+ <port id="3" precision="STRING" names="string_output">
247
+ <dim>-1</dim>
248
+ </port>
249
+ </output>
250
+ </layer>
251
+ <layer id="14" name="Result_282031" type="Result" version="opset1">
252
+ <input>
253
+ <port id="0" precision="STRING">
254
+ <dim>-1</dim>
255
+ </port>
256
+ </input>
257
+ </layer>
258
+ </layers>
259
+ <edges>
260
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
261
+ <edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
262
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
263
+ <edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
264
+ <edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
265
+ <edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
266
+ <edge from-layer="4" from-port="6" to-layer="7" to-port="0" />
267
+ <edge from-layer="4" from-port="7" to-layer="7" to-port="1" />
268
+ <edge from-layer="4" from-port="8" to-layer="7" to-port="2" />
269
+ <edge from-layer="4" from-port="5" to-layer="9" to-port="1" />
270
+ <edge from-layer="4" from-port="4" to-layer="9" to-port="0" />
271
+ <edge from-layer="5" from-port="0" to-layer="7" to-port="3" />
272
+ <edge from-layer="6" from-port="0" to-layer="7" to-port="4" />
273
+ <edge from-layer="7" from-port="7" to-layer="8" to-port="2" />
274
+ <edge from-layer="7" from-port="6" to-layer="8" to-port="1" />
275
+ <edge from-layer="7" from-port="5" to-layer="8" to-port="0" />
276
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="2" />
277
+ <edge from-layer="8" from-port="4" to-layer="9" to-port="3" />
278
+ <edge from-layer="8" from-port="5" to-layer="12" to-port="2" />
279
+ <edge from-layer="9" from-port="4" to-layer="12" to-port="0" />
280
+ <edge from-layer="9" from-port="5" to-layer="12" to-port="1" />
281
+ <edge from-layer="10" from-port="0" to-layer="12" to-port="3" />
282
+ <edge from-layer="11" from-port="0" to-layer="12" to-port="4" />
283
+ <edge from-layer="12" from-port="5" to-layer="13" to-port="0" />
284
+ <edge from-layer="12" from-port="6" to-layer="13" to-port="1" />
285
+ <edge from-layer="12" from-port="7" to-layer="13" to-port="2" />
286
+ <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
287
+ </edges>
288
+ <rt_info>
289
+ <bos_token_id value="1" />
290
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
291
+ <eos_token_id value="32000" />
292
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
293
+ <pad_token_id value="32000" />
294
+ </rt_info>
295
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
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
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }