Hugging Face's logo

ayjays132
/
PhillnetLargeQuantized

Text Generation
Transformers
PyTorch
English
gpt2
feature-extraction
text-generation-inference
Inference Endpoints
Model card Files Community
ayjays132 commited on
Commit
0e828ed
•
1 Parent(s): 4187132

Upload 6 files

Browse files
Files changed (5) hide show
  1. added_tokens.json +24 -14
  2. special_tokens_map.json +49 -4
  3. tokenizer.json +266 -2
  4. tokenizer_config.json +237 -4
  5. vocab.json +2 -2
added_tokens.json CHANGED
@@ -1,16 +1,26 @@
1
  {
2
- "amazeballs": 32104,
3
- "bromance": 32112,
4
- "crowdfunding": 32111,
5
- "cryptocurrency": 32105,
6
- "environment": 32103,
7
- "facepalm": 32110,
8
- "hangry": 32113,
9
- "happy": 32100,
10
- "intelligent": 32101,
11
- "photobomb": 32109,
12
- "response": 32102,
13
- "upcycle": 32108,
14
- "vlog": 32107,
15
- "webinar": 32106
 
 
 
 
 
 
 
 
 
 
16
  }
 
1
  {
2
+ "<apology>": 50268,
3
+ "<bos>": 50258,
4
+ "<cls>": 50263,
5
+ "<eos>": 50259,
6
+ "<farewell>": 50266,
7
+ "<greeting>": 50265,
8
+ "<mask>": 50264,
9
+ "<pad>": 50260,
10
+ "<sep>": 50262,
11
+ "<thank>": 50267,
12
+ "<unk>": 50261,
13
+ "<|pad|>": 50257,
14
+ "[PAD]": 50269,
15
+ "amazeballs": 50271,
16
+ "bromance": 50279,
17
+ "crowdfunding": 50278,
18
+ "cryptocurrency": 50272,
19
+ "facepalm": 50277,
20
+ "hangry": 50280,
21
+ "intelligent": 50270,
22
+ "photobomb": 50276,
23
+ "upcycle": 50275,
24
+ "vlog": 50274,
25
+ "webinar": 50273
26
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,51 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|pad|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<greeting>",
4
+ "<farewell>",
5
+ "<thank>",
6
+ "<apology>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<bos>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "cls_token": {
16
+ "content": "<cls>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "eos_token": {
23
+ "content": "<eos>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "mask_token": {
30
+ "content": "<mask>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "pad_token": "<eos>",
37
+ "sep_token": {
38
+ "content": "<sep>",
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 CHANGED
@@ -1,8 +1,56 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  {
7
  "id": 50256,
8
  "content": "<|endoftext|>",
@@ -11,6 +59,222 @@
11
  "rstrip": false,
12
  "normalized": true,
13
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
  ],
16
  "normalizer": null,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 50269,
14
+ "pad_type_id": 0,
15
+ "pad_token": "[PAD]"
16
+ },
17
  "added_tokens": [
18
+ {
19
+ "id": 11274,
20
+ "content": "good",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": true,
25
+ "special": false
26
+ },
27
+ {
28
+ "id": 26209,
29
+ "content": "response",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": true,
34
+ "special": false
35
+ },
36
+ {
37
+ "id": 34191,
38
+ "content": "happy",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true,
43
+ "special": false
44
+ },
45
+ {
46
+ "id": 38986,
47
+ "content": "environment",
48
+ "single_word": false,
49
+ "lstrip": false,
50
+ "rstrip": false,
51
+ "normalized": true,
52
+ "special": false
53
+ },
54
  {
55
  "id": 50256,
56
  "content": "<|endoftext|>",
 
59
  "rstrip": false,
60
  "normalized": true,
61
  "special": true
62
+ },
63
+ {
64
+ "id": 50257,
65
+ "content": "<|pad|>",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": false,
70
+ "special": true
71
+ },
72
+ {
73
+ "id": 50258,
74
+ "content": "<bos>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ {
82
+ "id": 50259,
83
+ "content": "<eos>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ {
91
+ "id": 50260,
92
+ "content": "<pad>",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": false,
97
+ "special": true
98
+ },
99
+ {
100
+ "id": 50261,
101
+ "content": "<unk>",
102
+ "single_word": false,
103
+ "lstrip": false,
104
+ "rstrip": false,
105
+ "normalized": false,
106
+ "special": true
107
+ },
108
+ {
109
+ "id": 50262,
110
+ "content": "<sep>",
111
+ "single_word": false,
112
+ "lstrip": false,
113
+ "rstrip": false,
114
+ "normalized": false,
115
+ "special": true
116
+ },
117
+ {
118
+ "id": 50263,
119
+ "content": "<cls>",
120
+ "single_word": false,
121
+ "lstrip": false,
122
+ "rstrip": false,
123
+ "normalized": false,
124
+ "special": true
125
+ },
126
+ {
127
+ "id": 50264,
128
+ "content": "<mask>",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": false,
133
+ "special": true
134
+ },
135
+ {
136
+ "id": 50265,
137
+ "content": "<greeting>",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": false,
142
+ "special": true
143
+ },
144
+ {
145
+ "id": 50266,
146
+ "content": "<farewell>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": true
152
+ },
153
+ {
154
+ "id": 50267,
155
+ "content": "<thank>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": true
161
+ },
162
+ {
163
+ "id": 50268,
164
+ "content": "<apology>",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": false,
169
+ "special": true
170
+ },
171
+ {
172
+ "id": 50269,
173
+ "content": "[PAD]",
174
+ "single_word": false,
175
+ "lstrip": false,
176
+ "rstrip": false,
177
+ "normalized": false,
178
+ "special": true
179
+ },
180
+ {
181
+ "id": 50270,
182
+ "content": "intelligent",
183
+ "single_word": false,
184
+ "lstrip": false,
185
+ "rstrip": false,
186
+ "normalized": true,
187
+ "special": false
188
+ },
189
+ {
190
+ "id": 50271,
191
+ "content": "amazeballs",
192
+ "single_word": false,
193
+ "lstrip": false,
194
+ "rstrip": false,
195
+ "normalized": true,
196
+ "special": false
197
+ },
198
+ {
199
+ "id": 50272,
200
+ "content": "cryptocurrency",
201
+ "single_word": false,
202
+ "lstrip": false,
203
+ "rstrip": false,
204
+ "normalized": true,
205
+ "special": false
206
+ },
207
+ {
208
+ "id": 50273,
209
+ "content": "webinar",
210
+ "single_word": false,
211
+ "lstrip": false,
212
+ "rstrip": false,
213
+ "normalized": true,
214
+ "special": false
215
+ },
216
+ {
217
+ "id": 50274,
218
+ "content": "vlog",
219
+ "single_word": false,
220
+ "lstrip": false,
221
+ "rstrip": false,
222
+ "normalized": true,
223
+ "special": false
224
+ },
225
+ {
226
+ "id": 50275,
227
+ "content": "upcycle",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": true,
232
+ "special": false
233
+ },
234
+ {
235
+ "id": 50276,
236
+ "content": "photobomb",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": true,
241
+ "special": false
242
+ },
243
+ {
244
+ "id": 50277,
245
+ "content": "facepalm",
246
+ "single_word": false,
247
+ "lstrip": false,
248
+ "rstrip": false,
249
+ "normalized": true,
250
+ "special": false
251
+ },
252
+ {
253
+ "id": 50278,
254
+ "content": "crowdfunding",
255
+ "single_word": false,
256
+ "lstrip": false,
257
+ "rstrip": false,
258
+ "normalized": true,
259
+ "special": false
260
+ },
261
+ {
262
+ "id": 50279,
263
+ "content": "bromance",
264
+ "single_word": false,
265
+ "lstrip": false,
266
+ "rstrip": false,
267
+ "normalized": true,
268
+ "special": false
269
+ },
270
+ {
271
+ "id": 50280,
272
+ "content": "hangry",
273
+ "single_word": false,
274
+ "lstrip": false,
275
+ "rstrip": false,
276
+ "normalized": true,
277
+ "special": false
278
  }
279
  ],
280
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -1,6 +1,38 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
@@ -8,13 +40,214 @@
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
 
 
 
 
 
 
14
  "clean_up_tokenization_spaces": true,
15
- "eos_token": "<|endoftext|>",
 
 
16
  "model_max_length": 1024,
17
- "pad_token": "<|pad|>",
 
18
  "tokenizer_class": "GPT2Tokenizer",
19
- "unk_token": "<|endoftext|>"
20
  }
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "11274": {
5
+ "content": "good",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "26209": {
13
+ "content": "response",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "34191": {
21
+ "content": "happy",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "38986": {
29
+ "content": "environment",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
  "50256": {
37
  "content": "<|endoftext|>",
38
  "lstrip": false,
 
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
+ },
44
+ "50257": {
45
+ "content": "<|pad|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50258": {
53
+ "content": "<bos>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50259": {
61
+ "content": "<eos>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50260": {
69
+ "content": "<pad>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50261": {
77
+ "content": "<unk>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50262": {
85
+ "content": "<sep>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50263": {
93
+ "content": "<cls>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50264": {
101
+ "content": "<mask>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50265": {
109
+ "content": "<greeting>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50266": {
117
+ "content": "<farewell>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50267": {
125
+ "content": "<thank>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50268": {
133
+ "content": "<apology>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50269": {
141
+ "content": "[PAD]",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50270": {
149
+ "content": "intelligent",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": "amazeballs",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": "cryptocurrency",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": "webinar",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": "vlog",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": "upcycle",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": "photobomb",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50277": {
205
+ "content": "facepalm",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50278": {
213
+ "content": "crowdfunding",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50279": {
221
+ "content": "bromance",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50280": {
229
+ "content": "hangry",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
  }
236
  },
237
+ "additional_special_tokens": [
238
+ "<greeting>",
239
+ "<farewell>",
240
+ "<thank>",
241
+ "<apology>"
242
+ ],
243
+ "bos_token": "<bos>",
244
  "clean_up_tokenization_spaces": true,
245
+ "cls_token": "<cls>",
246
+ "eos_token": "<eos>",
247
+ "mask_token": "<mask>",
248
  "model_max_length": 1024,
249
+ "pad_token": "<eos>",
250
+ "sep_token": "<sep>",
251
  "tokenizer_class": "GPT2Tokenizer",
252
+ "unk_token": "<unk>"
253
  }
vocab.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764a9f3d30c59cf2fd38ebccecea262aea53a4f8adfe0656584836f2898e380e
3
- size 43369111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2052635e337c0e877b3d02bbb8e64e3749499b355218dbdb2b74a7285f54da80
3
+ size 8109044