Hugging Face's logo

firqaaa
/
setfit-indo-absa-restaurant-aspect

Text Classification
setfit
Safetensors
sentence-transformers
bert
absa
generated_from_setfit_trainer
Eval Results
Model card Files Community
firqaaa commited on
Commit
c1f2148
•
1 Parent(s): bc6ecce

Add SetFit ABSA model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +7 -0
  2. README.md +365 -0
  3. config.json +47 -0
  4. config_sentence_transformers.json +7 -0
  5. config_setfit.json +9 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +37 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +64 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
README.md ADDED
@@ -0,0 +1,365 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - absa
6
+ - sentence-transformers
7
+ - text-classification
8
+ - generated_from_setfit_trainer
9
+ metrics:
10
+ - accuracy
11
+ widget:
12
+ - text: suasana:suasana ramai tapi suasana seperti bistro getaran tipe bistro
13
+ - text: makanan:dua kali terakhir saya memesan dari sini, makanan saya sangat pedas
14
+ sehingga saya hampir tidak bisa memakan, dan bumbu tersebut menghilangkan rasa
15
+ hidangan.
16
+ - text: tempat:makan di tempat, suasana menghemat, tetapi di meja anda, ini adalah
17
+ pengalaman yang sangat mengecewakan.
18
+ - text: suasana:mungkin agak ramai di akhir pekan, tapi suasana bagus dan ini adalah
19
+ makanan prancis terbaik yang bisa anda temukan di area tersebut penuh sesak
20
+ - text: porsi:mereka disajikan dengan hidangan pembuka gratis dan porsi cocok untuk
21
+ makan siang melayani
22
+ pipeline_tag: text-classification
23
+ inference: false
24
+ base_model: firqaaa/indo-sentence-bert-base
25
+ model-index:
26
+ - name: SetFit Aspect Model with firqaaa/indo-sentence-bert-base
27
+ results:
28
+ - task:
29
+ type: text-classification
30
+ name: Text Classification
31
+ dataset:
32
+ name: Unknown
33
+ type: unknown
34
+ split: test
35
+ metrics:
36
+ - type: accuracy
37
+ value: 0.8956953642384106
38
+ name: Accuracy
39
+ ---
40
+
41
+ # SetFit Aspect Model with firqaaa/indo-sentence-bert-base
42
+
43
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates.
44
+
45
+ The model has been trained using an efficient few-shot learning technique that involves:
46
+
47
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
48
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
49
+
50
+ This model was trained within the context of a larger system for ABSA, which looks like so:
51
+
52
+ 1. Use a spaCy model to select possible aspect span candidates.
53
+ 2. **Use this SetFit model to filter these possible aspect span candidates.**
54
+ 3. Use a SetFit model to classify the filtered aspect span candidates.
55
+
56
+ ## Model Details
57
+
58
+ ### Model Description
59
+ - **Model Type:** SetFit
60
+ - **Sentence Transformer body:** [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base)
61
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
62
+ - **spaCy Model:** id_core_news_trf
63
+ - **SetFitABSA Aspect Model:** [firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect](https://huggingface.co/firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect)
64
+ - **SetFitABSA Polarity Model:** [firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity](https://huggingface.co/firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity)
65
+ - **Maximum Sequence Length:** 512 tokens
66
+ - **Number of Classes:** 2 classes
67
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
68
+ <!-- - **Language:** Unknown -->
69
+ <!-- - **License:** Unknown -->
70
+
71
+ ### Model Sources
72
+
73
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
74
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
75
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
76
+
77
+ ### Model Labels
78
+ | Label | Examples |
79
+ |:----------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
80
+ | aspect | <ul><li>'reservasi:restoran ini sangat kecil sehingga reservasi adalah suatu keharusan.'</li><li>'nyonya rumah:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang nyonya rumah'</li><li>'busboy:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang.'</li></ul> |
81
+ | no aspect | <ul><li>'restoran:restoran ini sangat kecil sehingga reservasi adalah suatu keharusan.'</li><li>'keharusan:restoran ini sangat kecil sehingga reservasi adalah suatu keharusan.'</li><li>'sebelah kanan:di sebelah kanan saya, nyo rumah berdiri di dekat seorang busboy dan mendesiskan rapido, rapido ketika dia mencoba membersihkan dan mengatur ulang meja untuk enam orang nyonya rumah'</li></ul> |
82
+
83
+ ## Evaluation
84
+
85
+ ### Metrics
86
+ | Label | Accuracy |
87
+ |:--------|:---------|
88
+ | **all** | 0.8957 |
89
+
90
+ ## Uses
91
+
92
+ ### Direct Use for Inference
93
+
94
+ First install the SetFit library:
95
+
96
+ ```bash
97
+ pip install setfit
98
+ ```
99
+
100
+ Then you can load this model and run inference.
101
+
102
+ ```python
103
+ from setfit import AbsaModel
104
+
105
+ # Download from the 🤗 Hub
106
+ model = AbsaModel.from_pretrained(
107
+ "firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-aspect",
108
+ "firqaaa/indo-setfit-absa-sentence-bert-base-p1-restaurants-polarity",
109
+ )
110
+ # Run inference
111
+ preds = model("The food was great, but the venue is just way too busy.")
112
+ ```
113
+
114
+ <!--
115
+ ### Downstream Use
116
+
117
+ *List how someone could finetune this model on their own dataset.*
118
+ -->
119
+
120
+ <!--
121
+ ### Out-of-Scope Use
122
+
123
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
124
+ -->
125
+
126
+ <!--
127
+ ## Bias, Risks and Limitations
128
+
129
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
130
+ -->
131
+
132
+ <!--
133
+ ### Recommendations
134
+
135
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
136
+ -->
137
+
138
+ ## Training Details
139
+
140
+ ### Training Set Metrics
141
+ | Training set | Min | Median | Max |
142
+ |:-------------|:----|:--------|:----|
143
+ | Word count | 2 | 20.1601 | 59 |
144
+
145
+ | Label | Training Sample Count |
146
+ |:----------|:----------------------|
147
+ | no aspect | 2123 |
148
+ | aspect | 1076 |
149
+
150
+ ### Training Hyperparameters
151
+ - batch_size: (32, 32)
152
+ - num_epochs: (1, 1)
153
+ - max_steps: -1
154
+ - sampling_strategy: oversampling
155
+ - body_learning_rate: (2e-05, 1e-05)
156
+ - head_learning_rate: 0.01
157
+ - loss: CosineSimilarityLoss
158
+ - distance_metric: cosine_distance
159
+ - margin: 0.25
160
+ - end_to_end: False
161
+ - use_amp: True
162
+ - warmup_proportion: 0.1
163
+ - seed: 42
164
+ - eval_max_steps: -1
165
+ - load_best_model_at_end: True
166
+
167
+ ### Training Results
168
+ | Epoch | Step | Training Loss | Validation Loss |
169
+ |:----------:|:--------:|:-------------:|:---------------:|
170
+ | 0.0000 | 1 | 0.318 | - |
171
+ | 0.0003 | 50 | 0.285 | - |
172
+ | 0.0006 | 100 | 0.2917 | - |
173
+ | 0.0008 | 150 | 0.3018 | - |
174
+ | 0.0011 | 200 | 0.2513 | - |
175
+ | 0.0014 | 250 | 0.2847 | - |
176
+ | 0.0017 | 300 | 0.227 | - |
177
+ | 0.0020 | 350 | 0.2601 | - |
178
+ | 0.0023 | 400 | 0.241 | - |
179
+ | 0.0025 | 450 | 0.2765 | - |
180
+ | 0.0028 | 500 | 0.2799 | 0.2687 |
181
+ | 0.0031 | 550 | 0.2872 | - |
182
+ | 0.0034 | 600 | 0.2723 | - |
183
+ | 0.0037 | 650 | 0.2297 | - |
184
+ | 0.0040 | 700 | 0.2448 | - |
185
+ | 0.0042 | 750 | 0.3296 | - |
186
+ | 0.0045 | 800 | 0.2564 | - |
187
+ | 0.0048 | 850 | 0.2406 | - |
188
+ | 0.0051 | 900 | 0.2776 | - |
189
+ | 0.0054 | 950 | 0.246 | - |
190
+ | 0.0056 | 1000 | 0.2801 | 0.2589 |
191
+ | 0.0059 | 1050 | 0.2562 | - |
192
+ | 0.0062 | 1100 | 0.2639 | - |
193
+ | 0.0065 | 1150 | 0.2322 | - |
194
+ | 0.0068 | 1200 | 0.275 | - |
195
+ | 0.0071 | 1250 | 0.2568 | - |
196
+ | 0.0073 | 1300 | 0.2457 | - |
197
+ | 0.0076 | 1350 | 0.2367 | - |
198
+ | 0.0079 | 1400 | 0.2878 | - |
199
+ | 0.0082 | 1450 | 0.2297 | - |
200
+ | 0.0085 | 1500 | 0.2557 | 0.2506 |
201
+ | 0.0088 | 1550 | 0.241 | - |
202
+ | 0.0090 | 1600 | 0.252 | - |
203
+ | 0.0093 | 1650 | 0.2485 | - |
204
+ | 0.0096 | 1700 | 0.2562 | - |
205
+ | 0.0099 | 1750 | 0.2311 | - |
206
+ | 0.0102 | 1800 | 0.2222 | - |
207
+ | 0.0104 | 1850 | 0.212 | - |
208
+ | 0.0107 | 1900 | 0.2595 | - |
209
+ | 0.0110 | 1950 | 0.2293 | - |
210
+ | 0.0113 | 2000 | 0.1934 | 0.2393 |
211
+ | 0.0116 | 2050 | 0.2119 | - |
212
+ | 0.0119 | 2100 | 0.2109 | - |
213
+ | 0.0121 | 2150 | 0.1875 | - |
214
+ | 0.0124 | 2200 | 0.2096 | - |
215
+ | 0.0127 | 2250 | 0.1701 | - |
216
+ | 0.0130 | 2300 | 0.2227 | - |
217
+ | 0.0133 | 2350 | 0.1832 | - |
218
+ | 0.0135 | 2400 | 0.1838 | - |
219
+ | 0.0138 | 2450 | 0.1846 | - |
220
+ | 0.0141 | 2500 | 0.1452 | 0.186 |
221
+ | 0.0144 | 2550 | 0.1366 | - |
222
+ | 0.0147 | 2600 | 0.124 | - |
223
+ | 0.0150 | 2650 | 0.1385 | - |
224
+ | 0.0152 | 2700 | 0.0681 | - |
225
+ | 0.0155 | 2750 | 0.0811 | - |
226
+ | 0.0158 | 2800 | 0.0794 | - |
227
+ | 0.0161 | 2850 | 0.1466 | - |
228
+ | 0.0164 | 2900 | 0.0964 | - |
229
+ | 0.0167 | 2950 | 0.174 | - |
230
+ | 0.0169 | 3000 | 0.0116 | 0.1658 |
231
+ | 0.0172 | 3050 | 0.1171 | - |
232
+ | 0.0175 | 3100 | 0.0301 | - |
233
+ | 0.0178 | 3150 | 0.0568 | - |
234
+ | 0.0181 | 3200 | 0.0448 | - |
235
+ | 0.0183 | 3250 | 0.0353 | - |
236
+ | 0.0186 | 3300 | 0.0721 | - |
237
+ | 0.0189 | 3350 | 0.009 | - |
238
+ | 0.0192 | 3400 | 0.0367 | - |
239
+ | 0.0195 | 3450 | 0.0251 | - |
240
+ | 0.0198 | 3500 | 0.0323 | 0.1925 |
241
+ | 0.0200 | 3550 | 0.0286 | - |
242
+ | 0.0203 | 3600 | 0.0524 | - |
243
+ | 0.0206 | 3650 | 0.0404 | - |
244
+ | 0.0209 | 3700 | 0.0037 | - |
245
+ | 0.0212 | 3750 | 0.0365 | - |
246
+ | 0.0215 | 3800 | 0.0214 | - |
247
+ | 0.0217 | 3850 | 0.0769 | - |
248
+ | 0.0220 | 3900 | 0.0317 | - |
249
+ | 0.0223 | 3950 | 0.001 | - |
250
+ | 0.0226 | 4000 | 0.0115 | 0.1733 |
251
+ | 0.0229 | 4050 | 0.0553 | - |
252
+ | 0.0231 | 4100 | 0.0025 | - |
253
+ | 0.0234 | 4150 | 0.0023 | - |
254
+ | 0.0237 | 4200 | 0.0014 | - |
255
+ | 0.0240 | 4250 | 0.0306 | - |
256
+ | 0.0243 | 4300 | 0.0352 | - |
257
+ | 0.0246 | 4350 | 0.0009 | - |
258
+ | 0.0248 | 4400 | 0.0302 | - |
259
+ | 0.0251 | 4450 | 0.0026 | - |
260
+ | 0.0254 | 4500 | 0.0213 | 0.1793 |
261
+ | 0.0257 | 4550 | 0.0009 | - |
262
+ | 0.0260 | 4600 | 0.0315 | - |
263
+ | 0.0263 | 4650 | 0.0005 | - |
264
+ | 0.0265 | 4700 | 0.0005 | - |
265
+ | 0.0268 | 4750 | 0.0014 | - |
266
+ | 0.0271 | 4800 | 0.0503 | - |
267
+ | 0.0274 | 4850 | 0.0007 | - |
268
+ | 0.0277 | 4900 | 0.0012 | - |
269
+ | 0.0279 | 4950 | 0.001 | - |
270
+ | **0.0282** | **5000** | **0.0014** | **0.1525** |
271
+ | 0.0285 | 5050 | 0.0292 | - |
272
+ | 0.0288 | 5100 | 0.0004 | - |
273
+ | 0.0291 | 5150 | 0.0602 | - |
274
+ | 0.0294 | 5200 | 0.0292 | - |
275
+ | 0.0296 | 5250 | 0.0006 | - |
276
+ | 0.0299 | 5300 | 0.0009 | - |
277
+ | 0.0302 | 5350 | 0.0007 | - |
278
+ | 0.0305 | 5400 | 0.0823 | - |
279
+ | 0.0308 | 5450 | 0.0319 | - |
280
+ | 0.0311 | 5500 | 0.0005 | 0.1707 |
281
+ | 0.0313 | 5550 | 0.0003 | - |
282
+ | 0.0316 | 5600 | 0.0022 | - |
283
+ | 0.0319 | 5650 | 0.047 | - |
284
+ | 0.0322 | 5700 | 0.0299 | - |
285
+ | 0.0325 | 5750 | 0.0312 | - |
286
+ | 0.0327 | 5800 | 0.0004 | - |
287
+ | 0.0330 | 5850 | 0.0301 | - |
288
+ | 0.0333 | 5900 | 0.0002 | - |
289
+ | 0.0336 | 5950 | 0.1056 | - |
290
+ | 0.0339 | 6000 | 0.0345 | 0.1859 |
291
+ | 0.0342 | 6050 | 0.0005 | - |
292
+ | 0.0344 | 6100 | 0.0224 | - |
293
+ | 0.0347 | 6150 | 0.0004 | - |
294
+ | 0.0350 | 6200 | 0.0055 | - |
295
+ | 0.0353 | 6250 | 0.0307 | - |
296
+ | 0.0356 | 6300 | 0.0297 | - |
297
+ | 0.0358 | 6350 | 0.0627 | - |
298
+ | 0.0361 | 6400 | 0.0002 | - |
299
+ | 0.0364 | 6450 | 0.0216 | - |
300
+ | 0.0367 | 6500 | 0.001 | 0.1692 |
301
+ | 0.0370 | 6550 | 0.0046 | - |
302
+ | 0.0373 | 6600 | 0.031 | - |
303
+ | 0.0375 | 6650 | 0.0298 | - |
304
+ | 0.0378 | 6700 | 0.0003 | - |
305
+ | 0.0381 | 6750 | 0.0018 | - |
306
+ | 0.0384 | 6800 | 0.0002 | - |
307
+ | 0.0387 | 6850 | 0.0124 | - |
308
+ | 0.0390 | 6900 | 0.0002 | - |
309
+ | 0.0392 | 6950 | 0.0002 | - |
310
+ | 0.0395 | 7000 | 0.0002 | 0.1866 |
311
+ | 0.0398 | 7050 | 0.0001 | - |
312
+ | 0.0401 | 7100 | 0.0038 | - |
313
+ | 0.0404 | 7150 | 0.0296 | - |
314
+ | 0.0406 | 7200 | 0.0002 | - |
315
+ | 0.0409 | 7250 | 0.0032 | - |
316
+ | 0.0412 | 7300 | 0.001 | - |
317
+ | 0.0415 | 7350 | 0.0003 | - |
318
+ | 0.0418 | 7400 | 0.0369 | - |
319
+ | 0.0421 | 7450 | 0.0524 | - |
320
+ | 0.0423 | 7500 | 0.0002 | 0.1956 |
321
+
322
+ * The bold row denotes the saved checkpoint.
323
+ ### Framework Versions
324
+ - Python: 3.10.13
325
+ - SetFit: 1.0.3
326
+ - Sentence Transformers: 2.2.2
327
+ - spaCy: 3.7.4
328
+ - Transformers: 4.36.2
329
+ - PyTorch: 2.1.2+cu121
330
+ - Datasets: 2.16.1
331
+ - Tokenizers: 0.15.0
332
+
333
+ ## Citation
334
+
335
+ ### BibTeX
336
+ ```bibtex
337
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
338
+ doi = {10.48550/ARXIV.2209.11055},
339
+ url = {https://arxiv.org/abs/2209.11055},
340
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
341
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
342
+ title = {Efficient Few-Shot Learning Without Prompts},
343
+ publisher = {arXiv},
344
+ year = {2022},
345
+ copyright = {Creative Commons Attribution 4.0 International}
346
+ }
347
+ ```
348
+
349
+ <!--
350
+ ## Glossary
351
+
352
+ *Clearly define terms in order to be accessible across audiences.*
353
+ -->
354
+
355
+ <!--
356
+ ## Model Card Authors
357
+
358
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
359
+ -->
360
+
361
+ <!--
362
+ ## Model Card Contact
363
+
364
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
365
+ -->
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/step_5000/",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "BertModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "pooler_fc_size": 768,
37
+ "pooler_num_attention_heads": 12,
38
+ "pooler_num_fc_layers": 3,
39
+ "pooler_size_per_head": 128,
40
+ "pooler_type": "first_token_transform",
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.36.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 50000
47
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.20.1",
5
+ "pytorch": "1.11.0"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "no aspect",
4
+ "aspect"
5
+ ],
6
+ "spacy_model": "id_core_news_trf",
7
+ "span_context": 0,
8
+ "normalize_embeddings": false
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750a46f1d07228a858c136ad0509ec2a6dd52997af062fd530d8734cf58f4791
3
+ size 497787752
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011e8ba92930711af035d43595e1651e89bd77ceee14803306a69ccd46bcd5ce
3
+ size 6991
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff