Hugging Face's logo

NTIS
/
kepri-embedding

Feature Extraction
Transformers
PyTorch
roberta
text-embeddings-inference
Inference Endpoints
Model card Files Community
NTIS commited on
Commit
99647f3
•
1 Parent(s): 393fc20

Add SetFit model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +7 -0
  2. README.md +464 -3
  3. config.json +29 -0
  4. config_sentence_transformers.json +7 -0
  5. config_setfit.json +7 -0
  6. model_head.pkl +3 -0
  7. modules.json +14 -0
  8. pytorch_model.bin +3 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +9 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +24 -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 CHANGED
@@ -1,3 +1,464 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: jhgan/ko-sroberta-multitask
3
+ library_name: setfit
4
+ metrics:
5
+ - accuracy
6
+ pipeline_tag: text-classification
7
+ tags:
8
+ - setfit
9
+ - sentence-transformers
10
+ - text-classification
11
+ - generated_from_setfit_trainer
12
+ widget:
13
+ - text: 기업이 파산 신청을 할 때 채무자의 주된 책임 범위는 어떠한가요?
14
+ - text: 무선 전력 전송 기술을 이용한 스마트 가전기기를 설계 중이야. 이와 동일한 연구나 특허가 있는지 알아봐줘
15
+ - text: 회사 합병 시 소액주주의 권리 보호 방안은 어떤 방식으로 이루어지나요?
16
+ - text: 화재 예방 시스템 설계에 대한 연구를 수행하고 있어. 기존 연구에서 이와 관련된 유사한 시스템 설계도나 논문이 있는지 찾고 싶어
17
+ - text: 블랙홀 정보 역설에 대해 설명한 논문의 핵심 포인트를 짧게 집약해 줄래?
18
+ inference: true
19
+ model-index:
20
+ - name: SetFit with jhgan/ko-sroberta-multitask
21
+ results:
22
+ - task:
23
+ type: text-classification
24
+ name: Text Classification
25
+ dataset:
26
+ name: Unknown
27
+ type: unknown
28
+ split: test
29
+ metrics:
30
+ - type: accuracy
31
+ value: 0.9558823529411765
32
+ name: Accuracy
33
+ ---
34
+
35
+ # SetFit with jhgan/ko-sroberta-multitask
36
+
37
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask) 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.
38
+
39
+ The model has been trained using an efficient few-shot learning technique that involves:
40
+
41
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
42
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
43
+
44
+ ## Model Details
45
+
46
+ ### Model Description
47
+ - **Model Type:** SetFit
48
+ - **Sentence Transformer body:** [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask)
49
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
50
+ - **Maximum Sequence Length:** 128 tokens
51
+ - **Number of Classes:** 5 classes
52
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
53
+ <!-- - **Language:** Unknown -->
54
+ <!-- - **License:** Unknown -->
55
+
56
+ ### Model Sources
57
+
58
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
59
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
60
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
61
+
62
+ ### Model Labels
63
+ | Label | Examples |
64
+ |:-----------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
65
+ | 오탈자 탐지 | <ul><li>'경영 보고서 내용에 대한 오탈자를 검토하고 수정해 드릴 수 있을까요?'</li><li>'경영 보고서에 포함된 오탈자를 잡아 줄 수 있나요?'</li><li>'경쟁사 분석 항목 내 문장 구성의 오류를 지적해주겠습니까?'</li></ul> |
66
+ | 요약 | <ul><li>'(특정 특허번호)를 기반으로 한 발명의 전체적인 개념을 짧게 설명 부탁드립니다.'</li><li>'1장의 데이터 수집 기술에 대해 요약해주세요'</li><li>'2022년 경제 성장 동향에 관한 문서의 두 번째 챕터를 축약해 주세요.'</li></ul> |
67
+ | 유사문서 | <ul><li>'5G 통신 모듈 최적화에 관련된 프로젝트를 하고 있는데, 비슷한 내용의 프로젝트나 논문이 있는지 연결해서 말해줄래?'</li><li>'5nm 공정을 이용한 반도체 제조 방법에 대해 작성하고 있어. 이와 연관 있는 보고서나 논문이 있으면 찾아주세요'</li><li>'AI 기반 헬스케어 솔루션 개발에 관한 문헌 조사를 하고 있습니다. 와 같은 주제를 다룬 문서를 찾아줄 수 있을까요?'</li></ul> |
68
+ | 중복성 검토 | <ul><li>'5G 네트워크 최적화 기술을 연구 중입니다. 기존 연구와 어떤 부분이 중복되는지, 중복의 이유를 명확히 설명해줄 수 있나요?'</li><li>'감정 노동자의 복지 증진 방안을 찾고 있어요. 이와 동일한 주제로 진행된 다른 프로젝트가 있었는지 알려주실래요? 그리고 그 이유도 설명해주세요.'</li><li>'건물의 내진 설계 강화 방안을 조사하고 있는데 이에 연관된 기존 프로젝트가 무엇이 있는지 그리고 왜 겹치는지 말해줄래?'</li></ul> |
69
+ | 특화 지식정보 제공 | <ul><li>'3D 금속 배선 기술(HBM, TSV)의 도입으로 인한 전력 소비 감소 방안에는 어떤 것이 있는가요?'</li><li>'AI 워크로드를 처리하기 위한 반도체 아키텍처 설계에서는 어떤 전략들이 사용되나요?'</li><li>'B2B 마케팅에서 특히 효과적인 콘텐츠 형식이나 채널은 어떤 것이 많아요?'</li></ul> |
70
+
71
+ ## Evaluation
72
+
73
+ ### Metrics
74
+ | Label | Accuracy |
75
+ |:--------|:---------|
76
+ | **all** | 0.9559 |
77
+
78
+ ## Uses
79
+
80
+ ### Direct Use for Inference
81
+
82
+ First install the SetFit library:
83
+
84
+ ```bash
85
+ pip install setfit
86
+ ```
87
+
88
+ Then you can load this model and run inference.
89
+
90
+ ```python
91
+ from setfit import SetFitModel
92
+
93
+ # Download from the 🤗 Hub
94
+ model = SetFitModel.from_pretrained("NTIS/kepri-embedding")
95
+ # Run inference
96
+ preds = model("기업이 파산 신청을 할 때 채무자의 주된 책임 범위는 어떠한가요?")
97
+ ```
98
+
99
+ <!--
100
+ ### Downstream Use
101
+
102
+ *List how someone could finetune this model on their own dataset.*
103
+ -->
104
+
105
+ <!--
106
+ ### Out-of-Scope Use
107
+
108
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
109
+ -->
110
+
111
+ <!--
112
+ ## Bias, Risks and Limitations
113
+
114
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
115
+ -->
116
+
117
+ <!--
118
+ ### Recommendations
119
+
120
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
121
+ -->
122
+
123
+ ## Training Details
124
+
125
+ ### Training Set Metrics
126
+ | Training set | Min | Median | Max |
127
+ |:-------------|:----|:--------|:----|
128
+ | Word count | 6 | 12.4219 | 27 |
129
+
130
+ | Label | Training Sample Count |
131
+ |:--------|:----------------------|
132
+ | rag | 0 |
133
+ | general | 0 |
134
+
135
+ ### Training Hyperparameters
136
+ - batch_size: (64, 64)
137
+ - num_epochs: (4, 4)
138
+ - max_steps: -1
139
+ - sampling_strategy: oversampling
140
+ - body_learning_rate: (2e-05, 1e-05)
141
+ - head_learning_rate: 0.01
142
+ - loss: CosineSimilarityLoss
143
+ - distance_metric: cosine_distance
144
+ - margin: 0.25
145
+ - end_to_end: False
146
+ - use_amp: False
147
+ - warmup_proportion: 0.1
148
+ - seed: 42
149
+ - eval_max_steps: -1
150
+ - load_best_model_at_end: True
151
+
152
+ ### Training Results
153
+ | Epoch | Step | Training Loss | Validation Loss |
154
+ |:-------:|:---------:|:-------------:|:---------------:|
155
+ | 0.0003 | 1 | 0.1889 | - |
156
+ | 0.0153 | 50 | 0.1818 | - |
157
+ | 0.0306 | 100 | 0.1421 | - |
158
+ | 0.0459 | 150 | 0.0582 | - |
159
+ | 0.0612 | 200 | 0.0299 | - |
160
+ | 0.0765 | 250 | 0.0093 | - |
161
+ | 0.0918 | 300 | 0.0036 | - |
162
+ | 0.1071 | 350 | 0.001 | - |
163
+ | 0.1224 | 400 | 0.0012 | - |
164
+ | 0.1377 | 450 | 0.0006 | - |
165
+ | 0.1530 | 500 | 0.0006 | - |
166
+ | 0.1683 | 550 | 0.0003 | - |
167
+ | 0.1836 | 600 | 0.0003 | - |
168
+ | 0.1989 | 650 | 0.0003 | - |
169
+ | 0.2142 | 700 | 0.0002 | - |
170
+ | 0.2295 | 750 | 0.0002 | - |
171
+ | 0.2448 | 800 | 0.0002 | - |
172
+ | 0.2601 | 850 | 0.0001 | - |
173
+ | 0.2754 | 900 | 0.0001 | - |
174
+ | 0.2907 | 950 | 0.0001 | - |
175
+ | 0.3060 | 1000 | 0.0001 | - |
176
+ | 0.3213 | 1050 | 0.0001 | - |
177
+ | 0.3366 | 1100 | 0.0001 | - |
178
+ | 0.3519 | 1150 | 0.0001 | - |
179
+ | 0.3672 | 1200 | 0.0001 | - |
180
+ | 0.3825 | 1250 | 0.0001 | - |
181
+ | 0.3978 | 1300 | 0.0001 | - |
182
+ | 0.4131 | 1350 | 0.0001 | - |
183
+ | 0.4284 | 1400 | 0.0001 | - |
184
+ | 0.4437 | 1450 | 0.0001 | - |
185
+ | 0.4590 | 1500 | 0.0 | - |
186
+ | 0.4743 | 1550 | 0.0001 | - |
187
+ | 0.4896 | 1600 | 0.0 | - |
188
+ | 0.5049 | 1650 | 0.0001 | - |
189
+ | 0.5202 | 1700 | 0.0 | - |
190
+ | 0.5355 | 1750 | 0.0 | - |
191
+ | 0.5508 | 1800 | 0.0 | - |
192
+ | 0.5661 | 1850 | 0.0 | - |
193
+ | 0.5814 | 1900 | 0.0 | - |
194
+ | 0.5967 | 1950 | 0.0 | - |
195
+ | 0.6120 | 2000 | 0.0 | - |
196
+ | 0.6273 | 2050 | 0.0 | - |
197
+ | 0.6426 | 2100 | 0.0 | - |
198
+ | 0.6579 | 2150 | 0.0 | - |
199
+ | 0.6732 | 2200 | 0.0 | - |
200
+ | 0.6885 | 2250 | 0.0 | - |
201
+ | 0.7038 | 2300 | 0.0 | - |
202
+ | 0.7191 | 2350 | 0.0 | - |
203
+ | 0.7344 | 2400 | 0.0 | - |
204
+ | 0.7497 | 2450 | 0.0 | - |
205
+ | 0.7650 | 2500 | 0.0 | - |
206
+ | 0.7803 | 2550 | 0.0 | - |
207
+ | 0.7956 | 2600 | 0.0 | - |
208
+ | 0.8109 | 2650 | 0.0 | - |
209
+ | 0.8262 | 2700 | 0.0 | - |
210
+ | 0.8415 | 2750 | 0.0 | - |
211
+ | 0.8568 | 2800 | 0.0 | - |
212
+ | 0.8721 | 2850 | 0.0 | - |
213
+ | 0.8874 | 2900 | 0.0 | - |
214
+ | 0.9027 | 2950 | 0.0 | - |
215
+ | 0.9180 | 3000 | 0.0 | - |
216
+ | 0.9333 | 3050 | 0.0 | - |
217
+ | 0.9486 | 3100 | 0.0 | - |
218
+ | 0.9639 | 3150 | 0.0 | - |
219
+ | 0.9792 | 3200 | 0.0 | - |
220
+ | 0.9945 | 3250 | 0.0 | - |
221
+ | 1.0 | 3268 | - | 0.0497 |
222
+ | 1.0098 | 3300 | 0.0 | - |
223
+ | 1.0251 | 3350 | 0.0 | - |
224
+ | 1.0404 | 3400 | 0.0 | - |
225
+ | 1.0557 | 3450 | 0.0 | - |
226
+ | 1.0710 | 3500 | 0.0 | - |
227
+ | 1.0863 | 3550 | 0.0 | - |
228
+ | 1.1016 | 3600 | 0.0 | - |
229
+ | 1.1169 | 3650 | 0.0 | - |
230
+ | 1.1322 | 3700 | 0.0 | - |
231
+ | 1.1475 | 3750 | 0.0 | - |
232
+ | 1.1628 | 3800 | 0.0 | - |
233
+ | 1.1781 | 3850 | 0.0 | - |
234
+ | 1.1934 | 3900 | 0.0 | - |
235
+ | 1.2087 | 3950 | 0.0 | - |
236
+ | 1.2240 | 4000 | 0.0 | - |
237
+ | 1.2393 | 4050 | 0.0 | - |
238
+ | 1.2546 | 4100 | 0.0 | - |
239
+ | 1.2699 | 4150 | 0.0 | - |
240
+ | 1.2852 | 4200 | 0.0 | - |
241
+ | 1.3005 | 4250 | 0.0 | - |
242
+ | 1.3158 | 4300 | 0.0 | - |
243
+ | 1.3311 | 4350 | 0.0 | - |
244
+ | 1.3464 | 4400 | 0.0 | - |
245
+ | 1.3617 | 4450 | 0.0 | - |
246
+ | 1.3770 | 4500 | 0.0 | - |
247
+ | 1.3923 | 4550 | 0.0 | - |
248
+ | 1.4076 | 4600 | 0.0 | - |
249
+ | 1.4229 | 4650 | 0.0 | - |
250
+ | 1.4382 | 4700 | 0.0 | - |
251
+ | 1.4535 | 4750 | 0.0 | - |
252
+ | 1.4688 | 4800 | 0.0 | - |
253
+ | 1.4841 | 4850 | 0.0 | - |
254
+ | 1.4994 | 4900 | 0.0 | - |
255
+ | 1.5147 | 4950 | 0.0 | - |
256
+ | 1.5300 | 5000 | 0.0 | - |
257
+ | 1.5453 | 5050 | 0.0 | - |
258
+ | 1.5606 | 5100 | 0.0 | - |
259
+ | 1.5759 | 5150 | 0.0 | - |
260
+ | 1.5912 | 5200 | 0.0 | - |
261
+ | 1.6065 | 5250 | 0.0 | - |
262
+ | 1.6218 | 5300 | 0.0 | - |
263
+ | 1.6371 | 5350 | 0.0 | - |
264
+ | 1.6524 | 5400 | 0.0 | - |
265
+ | 1.6677 | 5450 | 0.0 | - |
266
+ | 1.6830 | 5500 | 0.0 | - |
267
+ | 1.6983 | 5550 | 0.0 | - |
268
+ | 1.7136 | 5600 | 0.0 | - |
269
+ | 1.7289 | 5650 | 0.0 | - |
270
+ | 1.7442 | 5700 | 0.0 | - |
271
+ | 1.7595 | 5750 | 0.0 | - |
272
+ | 1.7748 | 5800 | 0.0 | - |
273
+ | 1.7901 | 5850 | 0.0 | - |
274
+ | 1.8054 | 5900 | 0.0 | - |
275
+ | 1.8207 | 5950 | 0.0 | - |
276
+ | 1.8360 | 6000 | 0.0 | - |
277
+ | 1.8513 | 6050 | 0.0 | - |
278
+ | 1.8666 | 6100 | 0.0 | - |
279
+ | 1.8819 | 6150 | 0.0 | - |
280
+ | 1.8972 | 6200 | 0.0 | - |
281
+ | 1.9125 | 6250 | 0.0 | - |
282
+ | 1.9278 | 6300 | 0.0 | - |
283
+ | 1.9431 | 6350 | 0.0 | - |
284
+ | 1.9584 | 6400 | 0.0 | - |
285
+ | 1.9737 | 6450 | 0.0 | - |
286
+ | 1.9890 | 6500 | 0.0 | - |
287
+ | 2.0 | 6536 | - | 0.056 |
288
+ | 2.0043 | 6550 | 0.0 | - |
289
+ | 2.0196 | 6600 | 0.0 | - |
290
+ | 2.0349 | 6650 | 0.0 | - |
291
+ | 2.0502 | 6700 | 0.0 | - |
292
+ | 2.0655 | 6750 | 0.0 | - |
293
+ | 2.0808 | 6800 | 0.0 | - |
294
+ | 2.0961 | 6850 | 0.0 | - |
295
+ | 2.1114 | 6900 | 0.0 | - |
296
+ | 2.1267 | 6950 | 0.0 | - |
297
+ | 2.1420 | 7000 | 0.0 | - |
298
+ | 2.1573 | 7050 | 0.0 | - |
299
+ | 2.1726 | 7100 | 0.0 | - |
300
+ | 2.1879 | 7150 | 0.0 | - |
301
+ | 2.2032 | 7200 | 0.0 | - |
302
+ | 2.2185 | 7250 | 0.0 | - |
303
+ | 2.2338 | 7300 | 0.0 | - |
304
+ | 2.2491 | 7350 | 0.0 | - |
305
+ | 2.2644 | 7400 | 0.0 | - |
306
+ | 2.2797 | 7450 | 0.0 | - |
307
+ | 2.2950 | 7500 | 0.0 | - |
308
+ | 2.3103 | 7550 | 0.0 | - |
309
+ | 2.3256 | 7600 | 0.0 | - |
310
+ | 2.3409 | 7650 | 0.0 | - |
311
+ | 2.3562 | 7700 | 0.0 | - |
312
+ | 2.3715 | 7750 | 0.0 | - |
313
+ | 2.3868 | 7800 | 0.0 | - |
314
+ | 2.4021 | 7850 | 0.0 | - |
315
+ | 2.4174 | 7900 | 0.0 | - |
316
+ | 2.4327 | 7950 | 0.0 | - |
317
+ | 2.4480 | 8000 | 0.0 | - |
318
+ | 2.4633 | 8050 | 0.0 | - |
319
+ | 2.4786 | 8100 | 0.0 | - |
320
+ | 2.4939 | 8150 | 0.0 | - |
321
+ | 2.5092 | 8200 | 0.0 | - |
322
+ | 2.5245 | 8250 | 0.0 | - |
323
+ | 2.5398 | 8300 | 0.0 | - |
324
+ | 2.5551 | 8350 | 0.0 | - |
325
+ | 2.5704 | 8400 | 0.0 | - |
326
+ | 2.5857 | 8450 | 0.0 | - |
327
+ | 2.6010 | 8500 | 0.0 | - |
328
+ | 2.6163 | 8550 | 0.0 | - |
329
+ | 2.6316 | 8600 | 0.0 | - |
330
+ | 2.6469 | 8650 | 0.0 | - |
331
+ | 2.6622 | 8700 | 0.0 | - |
332
+ | 2.6775 | 8750 | 0.0 | - |
333
+ | 2.6928 | 8800 | 0.0 | - |
334
+ | 2.7081 | 8850 | 0.0 | - |
335
+ | 2.7234 | 8900 | 0.0 | - |
336
+ | 2.7387 | 8950 | 0.0 | - |
337
+ | 2.7540 | 9000 | 0.0 | - |
338
+ | 2.7693 | 9050 | 0.0 | - |
339
+ | 2.7846 | 9100 | 0.0 | - |
340
+ | 2.7999 | 9150 | 0.0 | - |
341
+ | 2.8152 | 9200 | 0.0 | - |
342
+ | 2.8305 | 9250 | 0.0 | - |
343
+ | 2.8458 | 9300 | 0.0 | - |
344
+ | 2.8611 | 9350 | 0.0 | - |
345
+ | 2.8764 | 9400 | 0.0 | - |
346
+ | 2.8917 | 9450 | 0.0 | - |
347
+ | 2.9070 | 9500 | 0.0 | - |
348
+ | 2.9223 | 9550 | 0.0 | - |
349
+ | 2.9376 | 9600 | 0.0 | - |
350
+ | 2.9529 | 9650 | 0.0 | - |
351
+ | 2.9682 | 9700 | 0.0 | - |
352
+ | 2.9835 | 9750 | 0.0 | - |
353
+ | 2.9988 | 9800 | 0.0 | - |
354
+ | 3.0 | 9804 | - | 0.061 |
355
+ | 3.0141 | 9850 | 0.0 | - |
356
+ | 3.0294 | 9900 | 0.0 | - |
357
+ | 3.0447 | 9950 | 0.0 | - |
358
+ | 3.0600 | 10000 | 0.0 | - |
359
+ | 3.0753 | 10050 | 0.0 | - |
360
+ | 3.0906 | 10100 | 0.0 | - |
361
+ | 3.1059 | 10150 | 0.0 | - |
362
+ | 3.1212 | 10200 | 0.0 | - |
363
+ | 3.1365 | 10250 | 0.0 | - |
364
+ | 3.1518 | 10300 | 0.0 | - |
365
+ | 3.1671 | 10350 | 0.0 | - |
366
+ | 3.1824 | 10400 | 0.0 | - |
367
+ | 3.1977 | 10450 | 0.0 | - |
368
+ | 3.2130 | 10500 | 0.0 | - |
369
+ | 3.2283 | 10550 | 0.0 | - |
370
+ | 3.2436 | 10600 | 0.0 | - |
371
+ | 3.2589 | 10650 | 0.0 | - |
372
+ | 3.2742 | 10700 | 0.0 | - |
373
+ | 3.2895 | 10750 | 0.0 | - |
374
+ | 3.3048 | 10800 | 0.0 | - |
375
+ | 3.3201 | 10850 | 0.0 | - |
376
+ | 3.3354 | 10900 | 0.0 | - |
377
+ | 3.3507 | 10950 | 0.0 | - |
378
+ | 3.3660 | 11000 | 0.0 | - |
379
+ | 3.3813 | 11050 | 0.0 | - |
380
+ | 3.3966 | 11100 | 0.0 | - |
381
+ | 3.4119 | 11150 | 0.0 | - |
382
+ | 3.4272 | 11200 | 0.0001 | - |
383
+ | 3.4425 | 11250 | 0.0 | - |
384
+ | 3.4578 | 11300 | 0.0 | - |
385
+ | 3.4731 | 11350 | 0.0 | - |
386
+ | 3.4884 | 11400 | 0.0 | - |
387
+ | 3.5037 | 11450 | 0.0 | - |
388
+ | 3.5190 | 11500 | 0.0 | - |
389
+ | 3.5343 | 11550 | 0.0 | - |
390
+ | 3.5496 | 11600 | 0.0 | - |
391
+ | 3.5649 | 11650 | 0.0 | - |
392
+ | 3.5802 | 11700 | 0.0 | - |
393
+ | 3.5955 | 11750 | 0.0 | - |
394
+ | 3.6108 | 11800 | 0.0 | - |
395
+ | 3.6261 | 11850 | 0.0 | - |
396
+ | 3.6414 | 11900 | 0.0 | - |
397
+ | 3.6567 | 11950 | 0.0 | - |
398
+ | 3.6720 | 12000 | 0.0 | - |
399
+ | 3.6873 | 12050 | 0.0 | - |
400
+ | 3.7026 | 12100 | 0.0 | - |
401
+ | 3.7179 | 12150 | 0.0 | - |
402
+ | 3.7332 | 12200 | 0.0 | - |
403
+ | 3.7485 | 12250 | 0.0 | - |
404
+ | 3.7638 | 12300 | 0.0 | - |
405
+ | 3.7791 | 12350 | 0.0 | - |
406
+ | 3.7944 | 12400 | 0.0 | - |
407
+ | 3.8097 | 12450 | 0.0 | - |
408
+ | 3.8250 | 12500 | 0.0 | - |
409
+ | 3.8403 | 12550 | 0.0 | - |
410
+ | 3.8556 | 12600 | 0.0 | - |
411
+ | 3.8709 | 12650 | 0.0 | - |
412
+ | 3.8862 | 12700 | 0.0 | - |
413
+ | 3.9015 | 12750 | 0.0 | - |
414
+ | 3.9168 | 12800 | 0.0 | - |
415
+ | 3.9321 | 12850 | 0.0 | - |
416
+ | 3.9474 | 12900 | 0.0 | - |
417
+ | 3.9627 | 12950 | 0.0 | - |
418
+ | 3.9780 | 13000 | 0.0 | - |
419
+ | 3.9933 | 13050 | 0.0 | - |
420
+ | **4.0** | **13072** | **-** | **0.0479** |
421
+
422
+ * The bold row denotes the saved checkpoint.
423
+ ### Framework Versions
424
+ - Python: 3.9.18
425
+ - SetFit: 1.0.3
426
+ - Sentence Transformers: 2.2.1
427
+ - Transformers: 4.32.1
428
+ - PyTorch: 1.10.0
429
+ - Datasets: 2.20.0
430
+ - Tokenizers: 0.13.3
431
+
432
+ ## Citation
433
+
434
+ ### BibTeX
435
+ ```bibtex
436
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
437
+ doi = {10.48550/ARXIV.2209.11055},
438
+ url = {https://arxiv.org/abs/2209.11055},
439
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
440
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
441
+ title = {Efficient Few-Shot Learning Without Prompts},
442
+ publisher = {arXiv},
443
+ year = {2022},
444
+ copyright = {Creative Commons Attribution 4.0 International}
445
+ }
446
+ ```
447
+
448
+ <!--
449
+ ## Glossary
450
+
451
+ *Clearly define terms in order to be accessible across audiences.*
452
+ -->
453
+
454
+ <!--
455
+ ## Model Card Authors
456
+
457
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
458
+ -->
459
+
460
+ <!--
461
+ ## Model Card Contact
462
+
463
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
464
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/step_13072/",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.32.1",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.1.0",
4
+ "transformers": "4.13.0",
5
+ "pytorch": "1.7.0+cu110"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": [
4
+ "rag",
5
+ "general"
6
+ ]
7
+ }
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b803e130af8176c6a5f09d4f0f4980d3b68fad01c59a87d6f32b1a4f959f7be7
3
+ size 31807
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1348e19b347964f5ae8a88b8622faca7925f98eb8f2e01802bd2246463e1fdf2
3
+ size 442537395
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_basic_tokenize": true,
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "mask_token": "[MASK]",
9
+ "max_length": 128,
10
+ "model_max_length": 512,
11
+ "never_split": null,
12
+ "pad_to_multiple_of": null,
13
+ "pad_token": "[PAD]",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
+ "sep_token": "[SEP]",
17
+ "stride": 0,
18
+ "strip_accents": null,
19
+ "tokenize_chinese_chars": true,
20
+ "tokenizer_class": "BertTokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
+ "unk_token": "[UNK]"
24
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff