Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +348 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +13 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- vocab.txt +0 -0
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 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
widget:
|
11 |
+
- text: What's today's date?
|
12 |
+
- text: Yes, please.
|
13 |
+
- text: I’d like to go to floor 2.
|
14 |
+
- text: Alright, floor 1 it is.
|
15 |
+
- text: Which floor can I find Martin Giese on?
|
16 |
+
pipeline_tag: text-classification
|
17 |
+
inference: true
|
18 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
19 |
+
---
|
20 |
+
|
21 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
22 |
+
|
23 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) 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.
|
24 |
+
|
25 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
26 |
+
|
27 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
28 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
29 |
+
|
30 |
+
## Model Details
|
31 |
+
|
32 |
+
### Model Description
|
33 |
+
- **Model Type:** SetFit
|
34 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
35 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
36 |
+
- **Maximum Sequence Length:** 512 tokens
|
37 |
+
- **Number of Classes:** 8 classes
|
38 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
39 |
+
<!-- - **Language:** Unknown -->
|
40 |
+
<!-- - **License:** Unknown -->
|
41 |
+
|
42 |
+
### Model Sources
|
43 |
+
|
44 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
45 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
46 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
47 |
+
|
48 |
+
### Model Labels
|
49 |
+
| Label | Examples |
|
50 |
+
|:------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------|
|
51 |
+
| RequestMoveToFloor | <ul><li>'Please go to the 3rd floor.'</li><li>'Can you take me to floor 5?'</li><li>'I need to go to the 8th floor.'</li></ul> |
|
52 |
+
| Confirm | <ul><li>"Yes, that's right."</li><li>'Sure.'</li><li>'Exactly.'</li></ul> |
|
53 |
+
| RequestEmployeeLocation | <ul><li>'Where is Erik Velldal’s office?'</li><li>'Which floor is Andreas Austeng on?'</li><li>'Can you tell me where Birthe Soppe’s office is?'</li></ul> |
|
54 |
+
| Feedback | <ul><li>'Okay, going to the 3rd floor.'</li><li>'Sure, heading to floor 5.'</li><li>'Understood, taking you to the 8th floor.'</li></ul> |
|
55 |
+
| Repeat | <ul><li>'Can you repeat that?'</li><li>'Sorry, I didn’t get that. Can you say it again?'</li><li>'What was that?'</li></ul> |
|
56 |
+
| CurrentFloor | <ul><li>'Which floor are we on?'</li><li>'What floor is this?'</li><li>'Are we on the 5th floor?'</li></ul> |
|
57 |
+
| Stop | <ul><li>'Stop the elevator.'</li><li>"Wait, don't go to that floor."</li><li>'No, not that floor.'</li></ul> |
|
58 |
+
| OutOfCoverage | <ul><li>"What's the capital of France?"</li><li>'How many floors does this building have?'</li><li>'Can you make a phone call for me?'</li></ul> |
|
59 |
+
|
60 |
+
## Uses
|
61 |
+
|
62 |
+
### Direct Use for Inference
|
63 |
+
|
64 |
+
First install the SetFit library:
|
65 |
+
|
66 |
+
```bash
|
67 |
+
pip install setfit
|
68 |
+
```
|
69 |
+
|
70 |
+
Then you can load this model and run inference.
|
71 |
+
|
72 |
+
```python
|
73 |
+
from setfit import SetFitModel
|
74 |
+
|
75 |
+
# Download from the 🤗 Hub
|
76 |
+
model = SetFitModel.from_pretrained("victomoe/setfit-intent-classifier")
|
77 |
+
# Run inference
|
78 |
+
preds = model("Yes, please.")
|
79 |
+
```
|
80 |
+
|
81 |
+
<!--
|
82 |
+
### Downstream Use
|
83 |
+
|
84 |
+
*List how someone could finetune this model on their own dataset.*
|
85 |
+
-->
|
86 |
+
|
87 |
+
<!--
|
88 |
+
### Out-of-Scope Use
|
89 |
+
|
90 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
91 |
+
-->
|
92 |
+
|
93 |
+
<!--
|
94 |
+
## Bias, Risks and Limitations
|
95 |
+
|
96 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
97 |
+
-->
|
98 |
+
|
99 |
+
<!--
|
100 |
+
### Recommendations
|
101 |
+
|
102 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
103 |
+
-->
|
104 |
+
|
105 |
+
## Training Details
|
106 |
+
|
107 |
+
### Training Set Metrics
|
108 |
+
| Training set | Min | Median | Max |
|
109 |
+
|:-------------|:----|:-------|:----|
|
110 |
+
| Word count | 1 | 5.2267 | 10 |
|
111 |
+
|
112 |
+
| Label | Training Sample Count |
|
113 |
+
|:------------------------|:----------------------|
|
114 |
+
| Confirm | 22 |
|
115 |
+
| CurrentFloor | 21 |
|
116 |
+
| Feedback | 22 |
|
117 |
+
| OutOfCoverage | 22 |
|
118 |
+
| Repeat | 20 |
|
119 |
+
| RequestEmployeeLocation | 22 |
|
120 |
+
| RequestMoveToFloor | 23 |
|
121 |
+
| Stop | 20 |
|
122 |
+
|
123 |
+
### Training Hyperparameters
|
124 |
+
- batch_size: (32, 32)
|
125 |
+
- num_epochs: (10, 10)
|
126 |
+
- max_steps: -1
|
127 |
+
- sampling_strategy: oversampling
|
128 |
+
- body_learning_rate: (2e-05, 1e-05)
|
129 |
+
- head_learning_rate: 0.01
|
130 |
+
- loss: CosineSimilarityLoss
|
131 |
+
- distance_metric: cosine_distance
|
132 |
+
- margin: 0.25
|
133 |
+
- end_to_end: False
|
134 |
+
- use_amp: False
|
135 |
+
- warmup_proportion: 0.1
|
136 |
+
- l2_weight: 0.01
|
137 |
+
- seed: 42
|
138 |
+
- eval_max_steps: -1
|
139 |
+
- load_best_model_at_end: False
|
140 |
+
|
141 |
+
### Training Results
|
142 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
143 |
+
|:------:|:----:|:-------------:|:---------------:|
|
144 |
+
| 0.0012 | 1 | 0.1997 | - |
|
145 |
+
| 0.0618 | 50 | 0.1876 | - |
|
146 |
+
| 0.1236 | 100 | 0.1623 | - |
|
147 |
+
| 0.1854 | 150 | 0.1266 | - |
|
148 |
+
| 0.2472 | 200 | 0.0748 | - |
|
149 |
+
| 0.3090 | 250 | 0.0417 | - |
|
150 |
+
| 0.3708 | 300 | 0.0236 | - |
|
151 |
+
| 0.4326 | 350 | 0.0094 | - |
|
152 |
+
| 0.4944 | 400 | 0.0041 | - |
|
153 |
+
| 0.5562 | 450 | 0.0028 | - |
|
154 |
+
| 0.6180 | 500 | 0.002 | - |
|
155 |
+
| 0.6799 | 550 | 0.0016 | - |
|
156 |
+
| 0.7417 | 600 | 0.0013 | - |
|
157 |
+
| 0.8035 | 650 | 0.0011 | - |
|
158 |
+
| 0.8653 | 700 | 0.0009 | - |
|
159 |
+
| 0.9271 | 750 | 0.0008 | - |
|
160 |
+
| 0.9889 | 800 | 0.0007 | - |
|
161 |
+
| 1.0507 | 850 | 0.0007 | - |
|
162 |
+
| 1.1125 | 900 | 0.0006 | - |
|
163 |
+
| 1.1743 | 950 | 0.0006 | - |
|
164 |
+
| 1.2361 | 1000 | 0.0005 | - |
|
165 |
+
| 1.2979 | 1050 | 0.0005 | - |
|
166 |
+
| 1.3597 | 1100 | 0.0004 | - |
|
167 |
+
| 1.4215 | 1150 | 0.0004 | - |
|
168 |
+
| 1.4833 | 1200 | 0.0004 | - |
|
169 |
+
| 1.5451 | 1250 | 0.0004 | - |
|
170 |
+
| 1.6069 | 1300 | 0.0004 | - |
|
171 |
+
| 1.6687 | 1350 | 0.0003 | - |
|
172 |
+
| 1.7305 | 1400 | 0.0003 | - |
|
173 |
+
| 1.7923 | 1450 | 0.0003 | - |
|
174 |
+
| 1.8541 | 1500 | 0.0003 | - |
|
175 |
+
| 1.9159 | 1550 | 0.0003 | - |
|
176 |
+
| 1.9778 | 1600 | 0.0003 | - |
|
177 |
+
| 2.0396 | 1650 | 0.0003 | - |
|
178 |
+
| 2.1014 | 1700 | 0.0003 | - |
|
179 |
+
| 2.1632 | 1750 | 0.0003 | - |
|
180 |
+
| 2.2250 | 1800 | 0.0002 | - |
|
181 |
+
| 2.2868 | 1850 | 0.0002 | - |
|
182 |
+
| 2.3486 | 1900 | 0.0002 | - |
|
183 |
+
| 2.4104 | 1950 | 0.0002 | - |
|
184 |
+
| 2.4722 | 2000 | 0.0002 | - |
|
185 |
+
| 2.5340 | 2050 | 0.0002 | - |
|
186 |
+
| 2.5958 | 2100 | 0.0002 | - |
|
187 |
+
| 2.6576 | 2150 | 0.0002 | - |
|
188 |
+
| 2.7194 | 2200 | 0.0002 | - |
|
189 |
+
| 2.7812 | 2250 | 0.0002 | - |
|
190 |
+
| 2.8430 | 2300 | 0.0002 | - |
|
191 |
+
| 2.9048 | 2350 | 0.0002 | - |
|
192 |
+
| 2.9666 | 2400 | 0.0002 | - |
|
193 |
+
| 3.0284 | 2450 | 0.0002 | - |
|
194 |
+
| 3.0902 | 2500 | 0.0002 | - |
|
195 |
+
| 3.1520 | 2550 | 0.0002 | - |
|
196 |
+
| 3.2138 | 2600 | 0.0002 | - |
|
197 |
+
| 3.2756 | 2650 | 0.0002 | - |
|
198 |
+
| 3.3375 | 2700 | 0.0002 | - |
|
199 |
+
| 3.3993 | 2750 | 0.0002 | - |
|
200 |
+
| 3.4611 | 2800 | 0.0002 | - |
|
201 |
+
| 3.5229 | 2850 | 0.0002 | - |
|
202 |
+
| 3.5847 | 2900 | 0.0002 | - |
|
203 |
+
| 3.6465 | 2950 | 0.0002 | - |
|
204 |
+
| 3.7083 | 3000 | 0.0002 | - |
|
205 |
+
| 3.7701 | 3050 | 0.0001 | - |
|
206 |
+
| 3.8319 | 3100 | 0.0001 | - |
|
207 |
+
| 3.8937 | 3150 | 0.0001 | - |
|
208 |
+
| 3.9555 | 3200 | 0.0001 | - |
|
209 |
+
| 4.0173 | 3250 | 0.0001 | - |
|
210 |
+
| 4.0791 | 3300 | 0.0001 | - |
|
211 |
+
| 4.1409 | 3350 | 0.0001 | - |
|
212 |
+
| 4.2027 | 3400 | 0.0001 | - |
|
213 |
+
| 4.2645 | 3450 | 0.0001 | - |
|
214 |
+
| 4.3263 | 3500 | 0.0001 | - |
|
215 |
+
| 4.3881 | 3550 | 0.0001 | - |
|
216 |
+
| 4.4499 | 3600 | 0.0001 | - |
|
217 |
+
| 4.5117 | 3650 | 0.0001 | - |
|
218 |
+
| 4.5735 | 3700 | 0.0001 | - |
|
219 |
+
| 4.6354 | 3750 | 0.0001 | - |
|
220 |
+
| 4.6972 | 3800 | 0.0001 | - |
|
221 |
+
| 4.7590 | 3850 | 0.0001 | - |
|
222 |
+
| 4.8208 | 3900 | 0.0001 | - |
|
223 |
+
| 4.8826 | 3950 | 0.0001 | - |
|
224 |
+
| 4.9444 | 4000 | 0.0001 | - |
|
225 |
+
| 5.0062 | 4050 | 0.0001 | - |
|
226 |
+
| 5.0680 | 4100 | 0.0001 | - |
|
227 |
+
| 5.1298 | 4150 | 0.0001 | - |
|
228 |
+
| 5.1916 | 4200 | 0.0001 | - |
|
229 |
+
| 5.2534 | 4250 | 0.0001 | - |
|
230 |
+
| 5.3152 | 4300 | 0.0001 | - |
|
231 |
+
| 5.3770 | 4350 | 0.0001 | - |
|
232 |
+
| 5.4388 | 4400 | 0.0001 | - |
|
233 |
+
| 5.5006 | 4450 | 0.0001 | - |
|
234 |
+
| 5.5624 | 4500 | 0.0001 | - |
|
235 |
+
| 5.6242 | 4550 | 0.0001 | - |
|
236 |
+
| 5.6860 | 4600 | 0.0001 | - |
|
237 |
+
| 5.7478 | 4650 | 0.0001 | - |
|
238 |
+
| 5.8096 | 4700 | 0.0001 | - |
|
239 |
+
| 5.8714 | 4750 | 0.0001 | - |
|
240 |
+
| 5.9333 | 4800 | 0.0001 | - |
|
241 |
+
| 5.9951 | 4850 | 0.0001 | - |
|
242 |
+
| 6.0569 | 4900 | 0.0001 | - |
|
243 |
+
| 6.1187 | 4950 | 0.0001 | - |
|
244 |
+
| 6.1805 | 5000 | 0.0001 | - |
|
245 |
+
| 6.2423 | 5050 | 0.0001 | - |
|
246 |
+
| 6.3041 | 5100 | 0.0001 | - |
|
247 |
+
| 6.3659 | 5150 | 0.0001 | - |
|
248 |
+
| 6.4277 | 5200 | 0.0001 | - |
|
249 |
+
| 6.4895 | 5250 | 0.0001 | - |
|
250 |
+
| 6.5513 | 5300 | 0.0001 | - |
|
251 |
+
| 6.6131 | 5350 | 0.0006 | - |
|
252 |
+
| 6.6749 | 5400 | 0.0001 | - |
|
253 |
+
| 6.7367 | 5450 | 0.0001 | - |
|
254 |
+
| 6.7985 | 5500 | 0.0001 | - |
|
255 |
+
| 6.8603 | 5550 | 0.0001 | - |
|
256 |
+
| 6.9221 | 5600 | 0.0001 | - |
|
257 |
+
| 6.9839 | 5650 | 0.0001 | - |
|
258 |
+
| 7.0457 | 5700 | 0.0001 | - |
|
259 |
+
| 7.1075 | 5750 | 0.0001 | - |
|
260 |
+
| 7.1693 | 5800 | 0.0001 | - |
|
261 |
+
| 7.2311 | 5850 | 0.0001 | - |
|
262 |
+
| 7.2930 | 5900 | 0.0001 | - |
|
263 |
+
| 7.3548 | 5950 | 0.0001 | - |
|
264 |
+
| 7.4166 | 6000 | 0.0001 | - |
|
265 |
+
| 7.4784 | 6050 | 0.0001 | - |
|
266 |
+
| 7.5402 | 6100 | 0.0001 | - |
|
267 |
+
| 7.6020 | 6150 | 0.0001 | - |
|
268 |
+
| 7.6638 | 6200 | 0.0001 | - |
|
269 |
+
| 7.7256 | 6250 | 0.0001 | - |
|
270 |
+
| 7.7874 | 6300 | 0.0001 | - |
|
271 |
+
| 7.8492 | 6350 | 0.0001 | - |
|
272 |
+
| 7.9110 | 6400 | 0.0001 | - |
|
273 |
+
| 7.9728 | 6450 | 0.0001 | - |
|
274 |
+
| 8.0346 | 6500 | 0.0007 | - |
|
275 |
+
| 8.0964 | 6550 | 0.0001 | - |
|
276 |
+
| 8.1582 | 6600 | 0.0001 | - |
|
277 |
+
| 8.2200 | 6650 | 0.0001 | - |
|
278 |
+
| 8.2818 | 6700 | 0.0001 | - |
|
279 |
+
| 8.3436 | 6750 | 0.0001 | - |
|
280 |
+
| 8.4054 | 6800 | 0.0001 | - |
|
281 |
+
| 8.4672 | 6850 | 0.0001 | - |
|
282 |
+
| 8.5290 | 6900 | 0.0001 | - |
|
283 |
+
| 8.5909 | 6950 | 0.0001 | - |
|
284 |
+
| 8.6527 | 7000 | 0.0001 | - |
|
285 |
+
| 8.7145 | 7050 | 0.0001 | - |
|
286 |
+
| 8.7763 | 7100 | 0.0001 | - |
|
287 |
+
| 8.8381 | 7150 | 0.0001 | - |
|
288 |
+
| 8.8999 | 7200 | 0.0001 | - |
|
289 |
+
| 8.9617 | 7250 | 0.0001 | - |
|
290 |
+
| 9.0235 | 7300 | 0.0001 | - |
|
291 |
+
| 9.0853 | 7350 | 0.0001 | - |
|
292 |
+
| 9.1471 | 7400 | 0.0001 | - |
|
293 |
+
| 9.2089 | 7450 | 0.0001 | - |
|
294 |
+
| 9.2707 | 7500 | 0.0001 | - |
|
295 |
+
| 9.3325 | 7550 | 0.0001 | - |
|
296 |
+
| 9.3943 | 7600 | 0.0001 | - |
|
297 |
+
| 9.4561 | 7650 | 0.0001 | - |
|
298 |
+
| 9.5179 | 7700 | 0.0001 | - |
|
299 |
+
| 9.5797 | 7750 | 0.0001 | - |
|
300 |
+
| 9.6415 | 7800 | 0.0001 | - |
|
301 |
+
| 9.7033 | 7850 | 0.0001 | - |
|
302 |
+
| 9.7651 | 7900 | 0.0001 | - |
|
303 |
+
| 9.8269 | 7950 | 0.0001 | - |
|
304 |
+
| 9.8888 | 8000 | 0.0001 | - |
|
305 |
+
| 9.9506 | 8050 | 0.0001 | - |
|
306 |
+
|
307 |
+
### Framework Versions
|
308 |
+
- Python: 3.10.8
|
309 |
+
- SetFit: 1.1.0
|
310 |
+
- Sentence Transformers: 3.1.1
|
311 |
+
- Transformers: 4.38.2
|
312 |
+
- PyTorch: 2.1.2
|
313 |
+
- Datasets: 2.17.1
|
314 |
+
- Tokenizers: 0.15.0
|
315 |
+
|
316 |
+
## Citation
|
317 |
+
|
318 |
+
### BibTeX
|
319 |
+
```bibtex
|
320 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
321 |
+
doi = {10.48550/ARXIV.2209.11055},
|
322 |
+
url = {https://arxiv.org/abs/2209.11055},
|
323 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
324 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
325 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
326 |
+
publisher = {arXiv},
|
327 |
+
year = {2022},
|
328 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
329 |
+
}
|
330 |
+
```
|
331 |
+
|
332 |
+
<!--
|
333 |
+
## Glossary
|
334 |
+
|
335 |
+
*Clearly define terms in order to be accessible across audiences.*
|
336 |
+
-->
|
337 |
+
|
338 |
+
<!--
|
339 |
+
## Model Card Authors
|
340 |
+
|
341 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
342 |
+
-->
|
343 |
+
|
344 |
+
<!--
|
345 |
+
## Model Card Contact
|
346 |
+
|
347 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
348 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.2",
|
23 |
+
"vocab_size": 30527
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.1.1",
|
4 |
+
"transformers": "4.38.2",
|
5 |
+
"pytorch": "2.1.2"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"normalize_embeddings": false,
|
3 |
+
"labels": [
|
4 |
+
"Confirm",
|
5 |
+
"CurrentFloor",
|
6 |
+
"Feedback",
|
7 |
+
"OutOfCoverage",
|
8 |
+
"Repeat",
|
9 |
+
"RequestEmployeeLocation",
|
10 |
+
"RequestMoveToFloor",
|
11 |
+
"Stop"
|
12 |
+
]
|
13 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21224102494baa4d78824d1705f49ccda704e47bd464abdc10abca7358154120
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0e7c900759bf46eb021c247218d98c1e57a08eab0503f8ac31e4991e182ba57
|
3 |
+
size 50775
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
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
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"104": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"30526": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": true,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"strip_accents": null,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "MPNetTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|