vedantjumle
commited on
Commit
•
1f41fbf
1
Parent(s):
b2d9d31
Training in progress epoch 0
Browse files- README.md +55 -0
- added_tokens.json +7 -0
- config.json +329 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-large-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: vedantjumle/bert-2
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# vedantjumle/bert-2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 4.9809
|
19 |
+
- Validation Loss: 4.7828
|
20 |
+
- Train Accuracy: 0.0333
|
21 |
+
- Epoch: 0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 4.9809 | 4.7828 | 0.0333 | 0 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.34.0
|
53 |
+
- TensorFlow 2.13.0
|
54 |
+
- Datasets 2.14.5
|
55 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 101,
|
3 |
+
"[MASK]": 103,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 102,
|
6 |
+
"[UNK]": 100
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15",
|
29 |
+
"16": "LABEL_16",
|
30 |
+
"17": "LABEL_17",
|
31 |
+
"18": "LABEL_18",
|
32 |
+
"19": "LABEL_19",
|
33 |
+
"20": "LABEL_20",
|
34 |
+
"21": "LABEL_21",
|
35 |
+
"22": "LABEL_22",
|
36 |
+
"23": "LABEL_23",
|
37 |
+
"24": "LABEL_24",
|
38 |
+
"25": "LABEL_25",
|
39 |
+
"26": "LABEL_26",
|
40 |
+
"27": "LABEL_27",
|
41 |
+
"28": "LABEL_28",
|
42 |
+
"29": "LABEL_29",
|
43 |
+
"30": "LABEL_30",
|
44 |
+
"31": "LABEL_31",
|
45 |
+
"32": "LABEL_32",
|
46 |
+
"33": "LABEL_33",
|
47 |
+
"34": "LABEL_34",
|
48 |
+
"35": "LABEL_35",
|
49 |
+
"36": "LABEL_36",
|
50 |
+
"37": "LABEL_37",
|
51 |
+
"38": "LABEL_38",
|
52 |
+
"39": "LABEL_39",
|
53 |
+
"40": "LABEL_40",
|
54 |
+
"41": "LABEL_41",
|
55 |
+
"42": "LABEL_42",
|
56 |
+
"43": "LABEL_43",
|
57 |
+
"44": "LABEL_44",
|
58 |
+
"45": "LABEL_45",
|
59 |
+
"46": "LABEL_46",
|
60 |
+
"47": "LABEL_47",
|
61 |
+
"48": "LABEL_48",
|
62 |
+
"49": "LABEL_49",
|
63 |
+
"50": "LABEL_50",
|
64 |
+
"51": "LABEL_51",
|
65 |
+
"52": "LABEL_52",
|
66 |
+
"53": "LABEL_53",
|
67 |
+
"54": "LABEL_54",
|
68 |
+
"55": "LABEL_55",
|
69 |
+
"56": "LABEL_56",
|
70 |
+
"57": "LABEL_57",
|
71 |
+
"58": "LABEL_58",
|
72 |
+
"59": "LABEL_59",
|
73 |
+
"60": "LABEL_60",
|
74 |
+
"61": "LABEL_61",
|
75 |
+
"62": "LABEL_62",
|
76 |
+
"63": "LABEL_63",
|
77 |
+
"64": "LABEL_64",
|
78 |
+
"65": "LABEL_65",
|
79 |
+
"66": "LABEL_66",
|
80 |
+
"67": "LABEL_67",
|
81 |
+
"68": "LABEL_68",
|
82 |
+
"69": "LABEL_69",
|
83 |
+
"70": "LABEL_70",
|
84 |
+
"71": "LABEL_71",
|
85 |
+
"72": "LABEL_72",
|
86 |
+
"73": "LABEL_73",
|
87 |
+
"74": "LABEL_74",
|
88 |
+
"75": "LABEL_75",
|
89 |
+
"76": "LABEL_76",
|
90 |
+
"77": "LABEL_77",
|
91 |
+
"78": "LABEL_78",
|
92 |
+
"79": "LABEL_79",
|
93 |
+
"80": "LABEL_80",
|
94 |
+
"81": "LABEL_81",
|
95 |
+
"82": "LABEL_82",
|
96 |
+
"83": "LABEL_83",
|
97 |
+
"84": "LABEL_84",
|
98 |
+
"85": "LABEL_85",
|
99 |
+
"86": "LABEL_86",
|
100 |
+
"87": "LABEL_87",
|
101 |
+
"88": "LABEL_88",
|
102 |
+
"89": "LABEL_89",
|
103 |
+
"90": "LABEL_90",
|
104 |
+
"91": "LABEL_91",
|
105 |
+
"92": "LABEL_92",
|
106 |
+
"93": "LABEL_93",
|
107 |
+
"94": "LABEL_94",
|
108 |
+
"95": "LABEL_95",
|
109 |
+
"96": "LABEL_96",
|
110 |
+
"97": "LABEL_97",
|
111 |
+
"98": "LABEL_98",
|
112 |
+
"99": "LABEL_99",
|
113 |
+
"100": "LABEL_100",
|
114 |
+
"101": "LABEL_101",
|
115 |
+
"102": "LABEL_102",
|
116 |
+
"103": "LABEL_103",
|
117 |
+
"104": "LABEL_104",
|
118 |
+
"105": "LABEL_105",
|
119 |
+
"106": "LABEL_106",
|
120 |
+
"107": "LABEL_107",
|
121 |
+
"108": "LABEL_108",
|
122 |
+
"109": "LABEL_109",
|
123 |
+
"110": "LABEL_110",
|
124 |
+
"111": "LABEL_111",
|
125 |
+
"112": "LABEL_112",
|
126 |
+
"113": "LABEL_113",
|
127 |
+
"114": "LABEL_114",
|
128 |
+
"115": "LABEL_115",
|
129 |
+
"116": "LABEL_116",
|
130 |
+
"117": "LABEL_117",
|
131 |
+
"118": "LABEL_118",
|
132 |
+
"119": "LABEL_119",
|
133 |
+
"120": "LABEL_120",
|
134 |
+
"121": "LABEL_121",
|
135 |
+
"122": "LABEL_122",
|
136 |
+
"123": "LABEL_123",
|
137 |
+
"124": "LABEL_124",
|
138 |
+
"125": "LABEL_125",
|
139 |
+
"126": "LABEL_126",
|
140 |
+
"127": "LABEL_127",
|
141 |
+
"128": "LABEL_128",
|
142 |
+
"129": "LABEL_129",
|
143 |
+
"130": "LABEL_130",
|
144 |
+
"131": "LABEL_131",
|
145 |
+
"132": "LABEL_132",
|
146 |
+
"133": "LABEL_133",
|
147 |
+
"134": "LABEL_134",
|
148 |
+
"135": "LABEL_135",
|
149 |
+
"136": "LABEL_136",
|
150 |
+
"137": "LABEL_137",
|
151 |
+
"138": "LABEL_138",
|
152 |
+
"139": "LABEL_139",
|
153 |
+
"140": "LABEL_140",
|
154 |
+
"141": "LABEL_141",
|
155 |
+
"142": "LABEL_142",
|
156 |
+
"143": "LABEL_143",
|
157 |
+
"144": "LABEL_144",
|
158 |
+
"145": "LABEL_145",
|
159 |
+
"146": "LABEL_146",
|
160 |
+
"147": "LABEL_147",
|
161 |
+
"148": "LABEL_148",
|
162 |
+
"149": "LABEL_149"
|
163 |
+
},
|
164 |
+
"initializer_range": 0.02,
|
165 |
+
"intermediate_size": 4096,
|
166 |
+
"label2id": {
|
167 |
+
"LABEL_0": 0,
|
168 |
+
"LABEL_1": 1,
|
169 |
+
"LABEL_10": 10,
|
170 |
+
"LABEL_100": 100,
|
171 |
+
"LABEL_101": 101,
|
172 |
+
"LABEL_102": 102,
|
173 |
+
"LABEL_103": 103,
|
174 |
+
"LABEL_104": 104,
|
175 |
+
"LABEL_105": 105,
|
176 |
+
"LABEL_106": 106,
|
177 |
+
"LABEL_107": 107,
|
178 |
+
"LABEL_108": 108,
|
179 |
+
"LABEL_109": 109,
|
180 |
+
"LABEL_11": 11,
|
181 |
+
"LABEL_110": 110,
|
182 |
+
"LABEL_111": 111,
|
183 |
+
"LABEL_112": 112,
|
184 |
+
"LABEL_113": 113,
|
185 |
+
"LABEL_114": 114,
|
186 |
+
"LABEL_115": 115,
|
187 |
+
"LABEL_116": 116,
|
188 |
+
"LABEL_117": 117,
|
189 |
+
"LABEL_118": 118,
|
190 |
+
"LABEL_119": 119,
|
191 |
+
"LABEL_12": 12,
|
192 |
+
"LABEL_120": 120,
|
193 |
+
"LABEL_121": 121,
|
194 |
+
"LABEL_122": 122,
|
195 |
+
"LABEL_123": 123,
|
196 |
+
"LABEL_124": 124,
|
197 |
+
"LABEL_125": 125,
|
198 |
+
"LABEL_126": 126,
|
199 |
+
"LABEL_127": 127,
|
200 |
+
"LABEL_128": 128,
|
201 |
+
"LABEL_129": 129,
|
202 |
+
"LABEL_13": 13,
|
203 |
+
"LABEL_130": 130,
|
204 |
+
"LABEL_131": 131,
|
205 |
+
"LABEL_132": 132,
|
206 |
+
"LABEL_133": 133,
|
207 |
+
"LABEL_134": 134,
|
208 |
+
"LABEL_135": 135,
|
209 |
+
"LABEL_136": 136,
|
210 |
+
"LABEL_137": 137,
|
211 |
+
"LABEL_138": 138,
|
212 |
+
"LABEL_139": 139,
|
213 |
+
"LABEL_14": 14,
|
214 |
+
"LABEL_140": 140,
|
215 |
+
"LABEL_141": 141,
|
216 |
+
"LABEL_142": 142,
|
217 |
+
"LABEL_143": 143,
|
218 |
+
"LABEL_144": 144,
|
219 |
+
"LABEL_145": 145,
|
220 |
+
"LABEL_146": 146,
|
221 |
+
"LABEL_147": 147,
|
222 |
+
"LABEL_148": 148,
|
223 |
+
"LABEL_149": 149,
|
224 |
+
"LABEL_15": 15,
|
225 |
+
"LABEL_16": 16,
|
226 |
+
"LABEL_17": 17,
|
227 |
+
"LABEL_18": 18,
|
228 |
+
"LABEL_19": 19,
|
229 |
+
"LABEL_2": 2,
|
230 |
+
"LABEL_20": 20,
|
231 |
+
"LABEL_21": 21,
|
232 |
+
"LABEL_22": 22,
|
233 |
+
"LABEL_23": 23,
|
234 |
+
"LABEL_24": 24,
|
235 |
+
"LABEL_25": 25,
|
236 |
+
"LABEL_26": 26,
|
237 |
+
"LABEL_27": 27,
|
238 |
+
"LABEL_28": 28,
|
239 |
+
"LABEL_29": 29,
|
240 |
+
"LABEL_3": 3,
|
241 |
+
"LABEL_30": 30,
|
242 |
+
"LABEL_31": 31,
|
243 |
+
"LABEL_32": 32,
|
244 |
+
"LABEL_33": 33,
|
245 |
+
"LABEL_34": 34,
|
246 |
+
"LABEL_35": 35,
|
247 |
+
"LABEL_36": 36,
|
248 |
+
"LABEL_37": 37,
|
249 |
+
"LABEL_38": 38,
|
250 |
+
"LABEL_39": 39,
|
251 |
+
"LABEL_4": 4,
|
252 |
+
"LABEL_40": 40,
|
253 |
+
"LABEL_41": 41,
|
254 |
+
"LABEL_42": 42,
|
255 |
+
"LABEL_43": 43,
|
256 |
+
"LABEL_44": 44,
|
257 |
+
"LABEL_45": 45,
|
258 |
+
"LABEL_46": 46,
|
259 |
+
"LABEL_47": 47,
|
260 |
+
"LABEL_48": 48,
|
261 |
+
"LABEL_49": 49,
|
262 |
+
"LABEL_5": 5,
|
263 |
+
"LABEL_50": 50,
|
264 |
+
"LABEL_51": 51,
|
265 |
+
"LABEL_52": 52,
|
266 |
+
"LABEL_53": 53,
|
267 |
+
"LABEL_54": 54,
|
268 |
+
"LABEL_55": 55,
|
269 |
+
"LABEL_56": 56,
|
270 |
+
"LABEL_57": 57,
|
271 |
+
"LABEL_58": 58,
|
272 |
+
"LABEL_59": 59,
|
273 |
+
"LABEL_6": 6,
|
274 |
+
"LABEL_60": 60,
|
275 |
+
"LABEL_61": 61,
|
276 |
+
"LABEL_62": 62,
|
277 |
+
"LABEL_63": 63,
|
278 |
+
"LABEL_64": 64,
|
279 |
+
"LABEL_65": 65,
|
280 |
+
"LABEL_66": 66,
|
281 |
+
"LABEL_67": 67,
|
282 |
+
"LABEL_68": 68,
|
283 |
+
"LABEL_69": 69,
|
284 |
+
"LABEL_7": 7,
|
285 |
+
"LABEL_70": 70,
|
286 |
+
"LABEL_71": 71,
|
287 |
+
"LABEL_72": 72,
|
288 |
+
"LABEL_73": 73,
|
289 |
+
"LABEL_74": 74,
|
290 |
+
"LABEL_75": 75,
|
291 |
+
"LABEL_76": 76,
|
292 |
+
"LABEL_77": 77,
|
293 |
+
"LABEL_78": 78,
|
294 |
+
"LABEL_79": 79,
|
295 |
+
"LABEL_8": 8,
|
296 |
+
"LABEL_80": 80,
|
297 |
+
"LABEL_81": 81,
|
298 |
+
"LABEL_82": 82,
|
299 |
+
"LABEL_83": 83,
|
300 |
+
"LABEL_84": 84,
|
301 |
+
"LABEL_85": 85,
|
302 |
+
"LABEL_86": 86,
|
303 |
+
"LABEL_87": 87,
|
304 |
+
"LABEL_88": 88,
|
305 |
+
"LABEL_89": 89,
|
306 |
+
"LABEL_9": 9,
|
307 |
+
"LABEL_90": 90,
|
308 |
+
"LABEL_91": 91,
|
309 |
+
"LABEL_92": 92,
|
310 |
+
"LABEL_93": 93,
|
311 |
+
"LABEL_94": 94,
|
312 |
+
"LABEL_95": 95,
|
313 |
+
"LABEL_96": 96,
|
314 |
+
"LABEL_97": 97,
|
315 |
+
"LABEL_98": 98,
|
316 |
+
"LABEL_99": 99
|
317 |
+
},
|
318 |
+
"layer_norm_eps": 1e-12,
|
319 |
+
"max_position_embeddings": 512,
|
320 |
+
"model_type": "bert",
|
321 |
+
"num_attention_heads": 16,
|
322 |
+
"num_hidden_layers": 24,
|
323 |
+
"pad_token_id": 0,
|
324 |
+
"position_embedding_type": "absolute",
|
325 |
+
"transformers_version": "4.34.0",
|
326 |
+
"type_vocab_size": 2,
|
327 |
+
"use_cache": true,
|
328 |
+
"vocab_size": 30522
|
329 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da079189db9ff51723b3144c83bf96e6caf6b65a3a01819493b96deda4896b9b
|
3 |
+
size 1341734528
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|