mjalg commited on
Commit
8957f3d
1 Parent(s): c9575d1

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +64 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +360 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<repo_name>",
9
+ "<file_sep>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<jupyter_script>",
18
+ "<empty_output>",
19
+ "<code_to_intermediate>",
20
+ "<intermediate_to_code>",
21
+ "<pr>",
22
+ "<pr_status>",
23
+ "<pr_is_merged>",
24
+ "<pr_base>",
25
+ "<pr_file>",
26
+ "<pr_base_code>",
27
+ "<pr_diff>",
28
+ "<pr_diff_hunk>",
29
+ "<pr_comment>",
30
+ "<pr_event_id>",
31
+ "<pr_review>",
32
+ "<pr_review_state>",
33
+ "<pr_review_comment>",
34
+ "<pr_in_reply_to_review_id>",
35
+ "<pr_in_reply_to_comment_id>",
36
+ "<pr_diff_hunk_comment_line>",
37
+ "<NAME>",
38
+ "<EMAIL>",
39
+ "<KEY>",
40
+ "<PASSWORD>"
41
+ ],
42
+ "bos_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "eos_token": {
50
+ "content": "<|endoftext|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "pad_token": "<|endoftext|>",
57
+ "unk_token": {
58
+ "content": "<|endoftext|>",
59
+ "lstrip": false,
60
+ "normalized": false,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,360 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<repo_name>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<file_sep>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_script>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<empty_output>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<code_to_intermediate>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<intermediate_to_code>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<pr>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "19": {
157
+ "content": "<pr_status>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "20": {
165
+ "content": "<pr_is_merged>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "21": {
173
+ "content": "<pr_base>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "22": {
181
+ "content": "<pr_file>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "23": {
189
+ "content": "<pr_base_code>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "24": {
197
+ "content": "<pr_diff>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "25": {
205
+ "content": "<pr_diff_hunk>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "26": {
213
+ "content": "<pr_comment>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "27": {
221
+ "content": "<pr_event_id>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "28": {
229
+ "content": "<pr_review>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "29": {
237
+ "content": "<pr_review_state>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "30": {
245
+ "content": "<pr_review_comment>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "31": {
253
+ "content": "<pr_in_reply_to_review_id>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32": {
261
+ "content": "<pr_in_reply_to_comment_id>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "33": {
269
+ "content": "<pr_diff_hunk_comment_line>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "34": {
277
+ "content": "<NAME>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "35": {
285
+ "content": "<EMAIL>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "36": {
293
+ "content": "<KEY>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "37": {
301
+ "content": "<PASSWORD>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ }
308
+ },
309
+ "additional_special_tokens": [
310
+ "<|endoftext|>",
311
+ "<fim_prefix>",
312
+ "<fim_middle>",
313
+ "<fim_suffix>",
314
+ "<fim_pad>",
315
+ "<repo_name>",
316
+ "<file_sep>",
317
+ "<issue_start>",
318
+ "<issue_comment>",
319
+ "<issue_closed>",
320
+ "<jupyter_start>",
321
+ "<jupyter_text>",
322
+ "<jupyter_code>",
323
+ "<jupyter_output>",
324
+ "<jupyter_script>",
325
+ "<empty_output>",
326
+ "<code_to_intermediate>",
327
+ "<intermediate_to_code>",
328
+ "<pr>",
329
+ "<pr_status>",
330
+ "<pr_is_merged>",
331
+ "<pr_base>",
332
+ "<pr_file>",
333
+ "<pr_base_code>",
334
+ "<pr_diff>",
335
+ "<pr_diff_hunk>",
336
+ "<pr_comment>",
337
+ "<pr_event_id>",
338
+ "<pr_review>",
339
+ "<pr_review_state>",
340
+ "<pr_review_comment>",
341
+ "<pr_in_reply_to_review_id>",
342
+ "<pr_in_reply_to_comment_id>",
343
+ "<pr_diff_hunk_comment_line>",
344
+ "<NAME>",
345
+ "<EMAIL>",
346
+ "<KEY>",
347
+ "<PASSWORD>"
348
+ ],
349
+ "bos_token": "<|endoftext|>",
350
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
351
+ "clean_up_tokenization_spaces": true,
352
+ "eos_token": "<|endoftext|>",
353
+ "model_max_length": 1000000000000000019884624838656,
354
+ "pad_token": "<|endoftext|>",
355
+ "padding_side": "left",
356
+ "split_special_tokens": false,
357
+ "tokenizer_class": "GPT2Tokenizer",
358
+ "unk_token": "<|endoftext|>",
359
+ "vocab_size": 49152
360
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff