mbley commited on
Commit
439b6d7
·
verified ·
1 Parent(s): 3622d18

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - setfit
4
+ - sentence-transformers
5
+ - text-classification
6
+ - generated_from_setfit_trainer
7
+ widget:
8
+ - text: 46 Abs. 2 BGG zum Beispiel die Schuldneranweisung gemäss den Bestimmungen
9
+ zum Schutz der ehelichen Gemeinschaft (Art. 177 ZGB; BGE 134 III 667), die Einsprache
10
+ gegen die Ausstellung einer Erbenbescheinigung (Art. 559 Abs. 1 ZGB; Urteil 5A_162/2007
11
+ vom 16. Juli 2007 E. 5.2) oder das Inventar über das Kindesvermögen (Art. 318
12
+ Abs. 2 ZGB; Urteil 5A_169/2007 vom 21. Juni 2007 E. 3).
13
+ - text: Im OP der Kinderklinik der MHH werden pro Jahr zwischen 1500 und 2000 Operationen
14
+ durchgeführt.
15
+ - text: Die Bindungen sollten anfangs in Fahrtrichtung zeigen.
16
+ - text: Raumausstatter gesucht, Recklinghausen
17
+ - text: Mehr Leistung durch Selbstgespräche
18
+ metrics:
19
+ - accuracy
20
+ pipeline_tag: text-classification
21
+ library_name: setfit
22
+ inference: false
23
+ ---
24
+
25
+ # SetFit
26
+
27
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification.
28
+
29
+ The model has been trained using an efficient few-shot learning technique that involves:
30
+
31
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
32
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
33
+
34
+ ## Model Details
35
+
36
+ ### Model Description
37
+ - **Model Type:** SetFit
38
+ <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
39
+ - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
40
+ - **Maximum Sequence Length:** 512 tokens
41
+ <!-- - **Number of Classes:** Unknown -->
42
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
43
+ <!-- - **Language:** Unknown -->
44
+ <!-- - **License:** Unknown -->
45
+
46
+ ### Model Sources
47
+
48
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
49
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
50
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
51
+
52
+ ## Uses
53
+
54
+ ### Direct Use for Inference
55
+
56
+ First install the SetFit library:
57
+
58
+ ```bash
59
+ pip install setfit
60
+ ```
61
+
62
+ Then you can load this model and run inference.
63
+
64
+ ```python
65
+ from setfit import SetFitModel
66
+
67
+ # Download from the 🤗 Hub
68
+ model = SetFitModel.from_pretrained("setfit_model_id")
69
+ # Run inference
70
+ preds = model("Mehr Leistung durch Selbstgespräche")
71
+ ```
72
+
73
+ <!--
74
+ ### Downstream Use
75
+
76
+ *List how someone could finetune this model on their own dataset.*
77
+ -->
78
+
79
+ <!--
80
+ ### Out-of-Scope Use
81
+
82
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
83
+ -->
84
+
85
+ <!--
86
+ ## Bias, Risks and Limitations
87
+
88
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
89
+ -->
90
+
91
+ <!--
92
+ ### Recommendations
93
+
94
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
95
+ -->
96
+
97
+ ## Training Details
98
+
99
+ ### Training Set Metrics
100
+ | Training set | Min | Median | Max |
101
+ |:-------------|:----|:--------|:----|
102
+ | Word count | 1 | 16.7450 | 201 |
103
+
104
+ ### Training Hyperparameters
105
+ - batch_size: (16, 32)
106
+ - num_epochs: (2, 32)
107
+ - max_steps: -1
108
+ - sampling_strategy: oversampling
109
+ - body_learning_rate: (2e-05, 1e-05)
110
+ - head_learning_rate: 0.01
111
+ - loss: CoSENTLoss
112
+ - distance_metric: cosine_distance
113
+ - margin: 0.25
114
+ - end_to_end: True
115
+ - use_amp: False
116
+ - warmup_proportion: 0.1
117
+ - l2_weight: 0.01
118
+ - max_length: 512
119
+ - seed: 13579
120
+ - eval_max_steps: -1
121
+ - load_best_model_at_end: False
122
+
123
+ ### Training Results
124
+ | Epoch | Step | Training Loss | Validation Loss |
125
+ |:------:|:-----:|:-------------:|:---------------:|
126
+ | 0.0001 | 1 | 3.2672 | - |
127
+ | 0.0119 | 100 | 5.7496 | - |
128
+ | 0.0239 | 200 | 4.7559 | - |
129
+ | 0.0358 | 300 | 4.2203 | - |
130
+ | 0.0477 | 400 | 4.0467 | - |
131
+ | 0.0596 | 500 | 3.9136 | - |
132
+ | 0.0716 | 600 | 3.791 | - |
133
+ | 0.0835 | 700 | 3.6316 | - |
134
+ | 0.0954 | 800 | 3.4742 | - |
135
+ | 0.1073 | 900 | 3.1001 | - |
136
+ | 0.1193 | 1000 | 2.4123 | - |
137
+ | 0.1312 | 1100 | 1.9843 | - |
138
+ | 0.1431 | 1200 | 1.9276 | - |
139
+ | 0.1551 | 1300 | 2.5268 | - |
140
+ | 0.1670 | 1400 | 2.229 | - |
141
+ | 0.1789 | 1500 | 2.0492 | - |
142
+ | 0.1908 | 1600 | 1.9396 | - |
143
+ | 0.2028 | 1700 | 1.6849 | - |
144
+ | 0.2147 | 1800 | 1.9385 | - |
145
+ | 0.2266 | 1900 | 1.6651 | - |
146
+ | 0.2385 | 2000 | 1.011 | - |
147
+ | 0.2505 | 2100 | 1.3135 | - |
148
+ | 0.2624 | 2200 | 1.347 | - |
149
+ | 0.2743 | 2300 | 1.4244 | - |
150
+ | 0.2863 | 2400 | 1.0954 | - |
151
+ | 0.2982 | 2500 | 0.9091 | - |
152
+ | 0.3101 | 2600 | 1.0739 | - |
153
+ | 0.3220 | 2700 | 0.9281 | - |
154
+ | 0.3340 | 2800 | 0.7909 | - |
155
+ | 0.3459 | 2900 | 0.5911 | - |
156
+ | 0.3578 | 3000 | 0.476 | - |
157
+ | 0.3698 | 3100 | 0.5782 | - |
158
+ | 0.3817 | 3200 | 0.4535 | - |
159
+ | 0.3936 | 3300 | 0.371 | - |
160
+ | 0.4055 | 3400 | 0.3692 | - |
161
+ | 0.4175 | 3500 | 0.2393 | - |
162
+ | 0.4294 | 3600 | 0.2623 | - |
163
+ | 0.4413 | 3700 | 0.2643 | - |
164
+ | 0.4532 | 3800 | 0.3065 | - |
165
+ | 0.4652 | 3900 | 0.2552 | - |
166
+ | 0.4771 | 4000 | 0.2093 | - |
167
+ | 0.4890 | 4100 | 0.217 | - |
168
+ | 0.5010 | 4200 | 0.1981 | - |
169
+ | 0.5129 | 4300 | 0.0827 | - |
170
+ | 0.5248 | 4400 | 0.1562 | - |
171
+ | 0.5367 | 4500 | 0.0438 | - |
172
+ | 0.5487 | 4600 | 0.0976 | - |
173
+ | 0.5606 | 4700 | 0.0307 | - |
174
+ | 0.5725 | 4800 | 0.0584 | - |
175
+ | 0.5844 | 4900 | 0.0503 | - |
176
+ | 0.5964 | 5000 | 0.0342 | - |
177
+ | 0.6083 | 5100 | 0.0244 | - |
178
+ | 0.6202 | 5200 | 0.0474 | - |
179
+ | 0.6322 | 5300 | 0.0346 | - |
180
+ | 0.6441 | 5400 | 0.0128 | - |
181
+ | 0.6560 | 5500 | 0.0077 | - |
182
+ | 0.6679 | 5600 | 0.0303 | - |
183
+ | 0.6799 | 5700 | 0.097 | - |
184
+ | 0.6918 | 5800 | 0.0152 | - |
185
+ | 0.7037 | 5900 | 0.0135 | - |
186
+ | 0.7156 | 6000 | 0.0222 | - |
187
+ | 0.7276 | 6100 | 0.0092 | - |
188
+ | 0.7395 | 6200 | 0.0277 | - |
189
+ | 0.7514 | 6300 | 0.0179 | - |
190
+ | 0.7634 | 6400 | 0.0092 | - |
191
+ | 0.7753 | 6500 | 0.0064 | - |
192
+ | 0.7872 | 6600 | 0.0176 | - |
193
+ | 0.7991 | 6700 | 0.0126 | - |
194
+ | 0.8111 | 6800 | 0.022 | - |
195
+ | 0.8230 | 6900 | 0.0187 | - |
196
+ | 0.8349 | 7000 | 0.0062 | - |
197
+ | 0.8469 | 7100 | 0.0031 | - |
198
+ | 0.8588 | 7200 | 0.0313 | - |
199
+ | 0.8707 | 7300 | 0.0026 | - |
200
+ | 0.8826 | 7400 | 0.0063 | - |
201
+ | 0.8946 | 7500 | 0.0008 | - |
202
+ | 0.9065 | 7600 | 0.0039 | - |
203
+ | 0.9184 | 7700 | 0.0009 | - |
204
+ | 0.9303 | 7800 | 0.001 | - |
205
+ | 0.9423 | 7900 | 0.0027 | - |
206
+ | 0.9542 | 8000 | 0.0023 | - |
207
+ | 0.9661 | 8100 | 0.0027 | - |
208
+ | 0.9781 | 8200 | 0.0022 | - |
209
+ | 0.9900 | 8300 | 0.0238 | - |
210
+ | 1.0019 | 8400 | 0.0008 | - |
211
+ | 1.0138 | 8500 | 0.0104 | - |
212
+ | 1.0258 | 8600 | 0.0014 | - |
213
+ | 1.0377 | 8700 | 0.0129 | - |
214
+ | 1.0496 | 8800 | 0.0014 | - |
215
+ | 1.0615 | 8900 | 0.002 | - |
216
+ | 1.0735 | 9000 | 0.0013 | - |
217
+ | 1.0854 | 9100 | 0.0046 | - |
218
+ | 1.0973 | 9200 | 0.0023 | - |
219
+ | 1.1093 | 9300 | 0.0023 | - |
220
+ | 1.1212 | 9400 | 0.0027 | - |
221
+ | 1.1331 | 9500 | 0.0021 | - |
222
+ | 1.1450 | 9600 | 0.0014 | - |
223
+ | 1.1570 | 9700 | 0.0036 | - |
224
+ | 1.1689 | 9800 | 0.0011 | - |
225
+ | 1.1808 | 9900 | 0.0027 | - |
226
+ | 1.1927 | 10000 | 0.0013 | - |
227
+ | 1.2047 | 10100 | 0.0007 | - |
228
+ | 1.2166 | 10200 | 0.0012 | - |
229
+ | 1.2285 | 10300 | 0.0033 | - |
230
+ | 1.2405 | 10400 | 0.0013 | - |
231
+ | 1.2524 | 10500 | 0.0008 | - |
232
+ | 1.2643 | 10600 | 0.0011 | - |
233
+ | 1.2762 | 10700 | 0.0007 | - |
234
+ | 1.2882 | 10800 | 0.0008 | - |
235
+ | 1.3001 | 10900 | 0.0005 | - |
236
+ | 1.3120 | 11000 | 0.0007 | - |
237
+ | 1.3240 | 11100 | 0.0015 | - |
238
+ | 1.3359 | 11200 | 0.0005 | - |
239
+ | 1.3478 | 11300 | 0.0011 | - |
240
+ | 1.3597 | 11400 | 0.001 | - |
241
+ | 1.3717 | 11500 | 0.0004 | - |
242
+ | 1.3836 | 11600 | 0.0015 | - |
243
+ | 1.3955 | 11700 | 0.0007 | - |
244
+ | 1.4074 | 11800 | 0.0007 | - |
245
+ | 1.4194 | 11900 | 0.0021 | - |
246
+ | 1.4313 | 12000 | 0.0004 | - |
247
+ | 1.4432 | 12100 | 0.0005 | - |
248
+ | 1.4552 | 12200 | 0.0007 | - |
249
+ | 1.4671 | 12300 | 0.0007 | - |
250
+ | 1.4790 | 12400 | 0.0015 | - |
251
+ | 1.4909 | 12500 | 0.0007 | - |
252
+ | 1.5029 | 12600 | 0.0004 | - |
253
+ | 1.5148 | 12700 | 0.0007 | - |
254
+ | 1.5267 | 12800 | 0.0017 | - |
255
+ | 1.5386 | 12900 | 0.0005 | - |
256
+ | 1.5506 | 13000 | 0.0006 | - |
257
+ | 1.5625 | 13100 | 0.0019 | - |
258
+ | 1.5744 | 13200 | 0.0004 | - |
259
+ | 1.5864 | 13300 | 0.0007 | - |
260
+ | 1.5983 | 13400 | 0.0005 | - |
261
+ | 1.6102 | 13500 | 0.0006 | - |
262
+ | 1.6221 | 13600 | 0.0003 | - |
263
+ | 1.6341 | 13700 | 0.0004 | - |
264
+ | 1.6460 | 13800 | 0.0003 | - |
265
+ | 1.6579 | 13900 | 0.0003 | - |
266
+ | 1.6698 | 14000 | 0.0006 | - |
267
+ | 1.6818 | 14100 | 0.0006 | - |
268
+ | 1.6937 | 14200 | 0.0003 | - |
269
+ | 1.7056 | 14300 | 0.0004 | - |
270
+ | 1.7176 | 14400 | 0.0003 | - |
271
+ | 1.7295 | 14500 | 0.0003 | - |
272
+ | 1.7414 | 14600 | 0.0003 | - |
273
+ | 1.7533 | 14700 | 0.0003 | - |
274
+ | 1.7653 | 14800 | 0.0004 | - |
275
+ | 1.7772 | 14900 | 0.0003 | - |
276
+ | 1.7891 | 15000 | 0.0003 | - |
277
+ | 1.8010 | 15100 | 0.0004 | - |
278
+ | 1.8130 | 15200 | 0.0004 | - |
279
+ | 1.8249 | 15300 | 0.0002 | - |
280
+ | 1.8368 | 15400 | 0.0003 | - |
281
+ | 1.8488 | 15500 | 0.0004 | - |
282
+ | 1.8607 | 15600 | 0.0003 | - |
283
+ | 1.8726 | 15700 | 0.0005 | - |
284
+ | 1.8845 | 15800 | 0.0004 | - |
285
+ | 1.8965 | 15900 | 0.0002 | - |
286
+ | 1.9084 | 16000 | 0.0002 | - |
287
+ | 1.9203 | 16100 | 0.0003 | - |
288
+ | 1.9323 | 16200 | 0.0003 | - |
289
+ | 1.9442 | 16300 | 0.0003 | - |
290
+ | 1.9561 | 16400 | 0.0004 | - |
291
+ | 1.9680 | 16500 | 0.0003 | - |
292
+ | 1.9800 | 16600 | 0.0002 | - |
293
+ | 1.9919 | 16700 | 0.0003 | - |
294
+
295
+ ### Framework Versions
296
+ - Python: 3.10.4
297
+ - SetFit: 1.1.2
298
+ - Sentence Transformers: 4.0.2
299
+ - Transformers: 4.51.1
300
+ - PyTorch: 2.6.0+cu126
301
+ - Datasets: 3.5.0
302
+ - Tokenizers: 0.21.1
303
+
304
+ ## Citation
305
+
306
+ ### BibTeX
307
+ ```bibtex
308
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
309
+ doi = {10.48550/ARXIV.2209.11055},
310
+ url = {https://arxiv.org/abs/2209.11055},
311
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
312
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
313
+ title = {Efficient Few-Shot Learning Without Prompts},
314
+ publisher = {arXiv},
315
+ year = {2022},
316
+ copyright = {Creative Commons Attribution 4.0 International}
317
+ }
318
+ ```
319
+
320
+ <!--
321
+ ## Glossary
322
+
323
+ *Clearly define terms in order to be accessible across audiences.*
324
+ -->
325
+
326
+ <!--
327
+ ## Model Card Authors
328
+
329
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
330
+ -->
331
+
332
+ <!--
333
+ ## Model Card Contact
334
+
335
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
336
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertModel"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "output_past": true,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": true,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.51.1",
23
+ "vocab_size": 31102
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "4.0.2",
4
+ "transformers": "4.51.1",
5
+ "pytorch": "2.6.0+cu126"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a996c8b091c0593bd26cadb54fb7e6b9d739c24ab6e034b38cc9508d6907e4
3
+ size 267244368
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee06aadeca647c6977b378f48a2971662993c8d2f272e292e67ec2e42caf132
3
+ size 23064
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
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
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
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": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff