Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +289 -0
- config.json +26 -0
- config_sentence_transformers.json +9 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Tiong Bahru Plaza, DDC-L2-5, AHU-L2-03 trip alarm
|
12 |
+
- text: 'Tiong Bahru Plaza, DDC L4-1, PAU-L4-03 supply air temperature (Units: °C).2'
|
13 |
+
- text: Tiong Bahru Plaza, DDC-L20, AHU 20-1 VSD CONTROL
|
14 |
+
- text: 'Tiong Bahru Plaza, VAV 19-7, Discharge Air Flow (Units: m3/h)'
|
15 |
+
- text: Tiong Bahru Plaza, DDC-L2-5, PAU-L2-02 VSD control
|
16 |
+
pipeline_tag: text-classification
|
17 |
+
inference: true
|
18 |
+
base_model: sentence-transformers/paraphrase-MiniLM-L3-v2
|
19 |
+
model-index:
|
20 |
+
- name: SetFit with sentence-transformers/paraphrase-MiniLM-L3-v2
|
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: 0.9777227722772277
|
32 |
+
name: Accuracy
|
33 |
+
---
|
34 |
+
|
35 |
+
# SetFit with sentence-transformers/paraphrase-MiniLM-L3-v2
|
36 |
+
|
37 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-MiniLM-L3-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L3-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.
|
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:** [sentence-transformers/paraphrase-MiniLM-L3-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L3-v2)
|
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:** 44 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 |
+
| 2 | <ul><li>'Tiong Bahru Plaza, DDC-L2-2, AHU-L2-05 FAD feedback'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 FAD Feedback'</li></ul> |
|
66 |
+
| 32 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 1 CHW Flowrate'</li><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Chilled Water Flow'</li></ul> |
|
67 |
+
| 1 | <ul><li>'Tiong Bahru Plaza, DDC-L2-5, PAU-L2-02 static pressure (Units: Pa)'</li><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-05 Static pressure (Units: Pa)'</li></ul> |
|
68 |
+
| 30 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temperature'</li></ul> |
|
69 |
+
| 42 | <ul><li>'Tiong Bahru Plaza, UC800_102004, Cond Leaving Water Temp (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_102004, Cond Leaving Water Temp (Units: °C)'</li></ul> |
|
70 |
+
| 13 | <ul><li>'Tiong Bahru Plaza, DDC L12, AHU 10-1 SMOKE ALARM'</li><li>'Tiong Bahru Plaza, DDC-L17, AHU 17-1 Smoke Alarm'</li></ul> |
|
71 |
+
| 35 | <ul><li>'Tiong Bahru Plaza, UC800_3, Condenser Saturated Refrigerant Temperature Circuit 1 (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_102004, Cond Saturated Refrigerant Temp Sensor Chiller'</li></ul> |
|
72 |
+
| 21 | <ul><li>'Tiong Bahru Plaza, VAV 19-14, Air Flow Setpoint Active (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV 19-22, Air Flow Setpoint Active (Units: m3/h)'</li></ul> |
|
73 |
+
| 19 | <ul><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor humidity (Units: %).1'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor humidity (Units: %)'</li></ul> |
|
74 |
+
| 14 | <ul><li>'Tiong Bahru Plaza, DDC-L1-5, AHU-L3-04A trip alarm'</li><li>'Tiong Bahru Plaza, DDC-L17, AHU 16-1 Trip Alarm'</li></ul> |
|
75 |
+
| 20 | <ul><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor temperature (Units: °C).1'</li></ul> |
|
76 |
+
| 12 | <ul><li>'Tiong Bahru Plaza, DDC-L1-5, PAU-L1-06 on/off status'</li><li>'Tiong Bahru Plaza, DDC-L20, PAHU TR-1(R-1) ON/OFF STATUS'</li></ul> |
|
77 |
+
| 39 | <ul><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Evaporator Refrigerant Pressure - Circuit 1 (Units: Pa)'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Evaporator Refrigerant Pressure - Circuit 1 (Units: Pa)'</li></ul> |
|
78 |
+
| 0 | <ul><li>'Tiong Bahru Plaza, DDC-L20, Co2 Level 18'</li><li>'Tiong Bahru Plaza, DDC-L17, AHU 16-1 CO2 reading'</li></ul> |
|
79 |
+
| 9 | <ul><li>'Tiong Bahru Plaza, DDC-L2-5, PAU-L2-02 supply air temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC L4-1, PAU-L4-02 supply air temperature (Units: °C).2'</li></ul> |
|
80 |
+
| 18 | <ul><li>'Tiong Bahru Plaza, DDC L2-4, AHU L2-04 switch mode'</li><li>'Tiong Bahru Plaza, DDC-L3-3, AHU-L3-1 switch mode'</li></ul> |
|
81 |
+
| 16 | <ul><li>'Tiong Bahru Plaza, VAV 19-18, Discharge Air Flow (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV 19-5, Discharge Air Flow (Units: m3/h)'</li></ul> |
|
82 |
+
| 8 | <ul><li>'Tiong Bahru Plaza, DDC-L1-3, AHU-L1-02 returm air temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-L1-1, AHU-L1-01 returm air temperature (Units: °C)'</li></ul> |
|
83 |
+
| 3 | <ul><li>'Tiong Bahru Plaza, DDC-L20, L20 Fresh air damper control (Units: %)'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 FAD Control'</li></ul> |
|
84 |
+
| 28 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CW Flowrate'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Chilled Water Flow'</li></ul> |
|
85 |
+
| 10 | <ul><li>'Tiong Bahru Plaza, DDC-L4-4, PAU-L4-01 VSD feedback'</li><li>'DDC-CH-3:CWP 3 VSD Feedback'</li></ul> |
|
86 |
+
| 38 | <ul><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Entering Condenser Water (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_3, Entering Condenser Water (Units: °C)'</li></ul> |
|
87 |
+
| 43 | <ul><li>'Tiong Bahru Plaza, VAV 19-6, Air Valve Position (Units: %).1'</li><li>'Tiong Bahru Plaza, VAV 19-11, Air Valve Position (Units: %)'</li></ul> |
|
88 |
+
| 36 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 3 CWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 3 CHWR Temperature'</li></ul> |
|
89 |
+
| 31 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Head CWR Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWR Temperature'</li></ul> |
|
90 |
+
| 26 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWS Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWS Temp'</li></ul> |
|
91 |
+
| 27 | <ul><li>'Tiong Bahru Plaza, MB-1-S3, Active Power kW'</li><li>'Tiong Bahru Plaza, MB-1-S2, Active Power kW'</li></ul> |
|
92 |
+
| 37 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CWS Temperature'</li></ul> |
|
93 |
+
| 34 | <ul><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Operating Mode'</li><li>'CT 3-1 Switch Mode'</li></ul> |
|
94 |
+
| 29 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWR Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWR Temperature'</li></ul> |
|
95 |
+
| 11 | <ul><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-05 Start/Stop Control'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU12-1 Start/Stop'</li></ul> |
|
96 |
+
| 7 | <ul><li>'Tiong Bahru Plaza, DDC-L2-2, AHU-L2-05 modulating valve feedback'</li><li>'Tiong Bahru Plaza, DDC L4-1, PAU-L4-02 modulating valve feedback (Units: %).3'</li></ul> |
|
97 |
+
| 22 | <ul><li>'Tiong Bahru Plaza, VAV 19-6, Active Setpoint (Units: °C).1'</li><li>'Tiong Bahru Plaza, VAV 19-16, Active Setpoint (Units: °C)'</li></ul> |
|
98 |
+
| 4 | <ul><li>'Tiong Bahru Plaza, DDC-L6, AHU 5-3 Flow'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 Flow'</li></ul> |
|
99 |
+
| 15 | <ul><li>'Tiong Bahru Plaza, VAV 19-17A, Space Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-19, Space Temperature (Units: °C)'</li></ul> |
|
100 |
+
| 25 | <ul><li>'Tiong Bahru Plaza, DDC-L1-3, AHU-L2-02 VSD control'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU 15-1 VSD CONTROL (Units: %)'</li></ul> |
|
101 |
+
| 23 | <ul><li>'Tiong Bahru Plaza, DDC B1-3, Pau-B1-02-DP Sensor'</li></ul> |
|
102 |
+
| 41 | <ul><li>' Chiller SC:Header Differential Pressure'</li></ul> |
|
103 |
+
| 17 | <ul><li>'Tiong Bahru Plaza, VAV 19-15, Discharge Air Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-6, Discharge Air Temperature (Units: °C)'</li></ul> |
|
104 |
+
| 5 | <ul><li>'Tiong Bahru Plaza, DDC-L20, AHU 19-1 OCT (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-L17, AHU 16-1 OCT (Units: °C)'</li></ul> |
|
105 |
+
| 40 | <ul><li>'Wet Bulb Temperature'</li></ul> |
|
106 |
+
| 33 | <ul><li>'Tiong Bahru Plaza, UC800_102004, Cond Water Flow'</li><li>'Tiong Bahru Plaza, UC800_102005, Cond Water Flow'</li></ul> |
|
107 |
+
| 24 | <ul><li>'Tiong Bahru Plaza, DDC-L20, PAHU TR-1 TEMPERATURE (Units: °C)'</li></ul> |
|
108 |
+
| 6 | <ul><li>'Tiong Bahru Plaza, DDC-L17, AHU 16-1 Valve Control (Units: %)'</li><li>'Tiong Bahru Plaza, DDC-L20, AHU 20-1 VALVE CONTROL (Units: %)'</li></ul> |
|
109 |
+
|
110 |
+
## Evaluation
|
111 |
+
|
112 |
+
### Metrics
|
113 |
+
| Label | Accuracy |
|
114 |
+
|:--------|:---------|
|
115 |
+
| **all** | 0.9777 |
|
116 |
+
|
117 |
+
## Uses
|
118 |
+
|
119 |
+
### Direct Use for Inference
|
120 |
+
|
121 |
+
First install the SetFit library:
|
122 |
+
|
123 |
+
```bash
|
124 |
+
pip install setfit
|
125 |
+
```
|
126 |
+
|
127 |
+
Then you can load this model and run inference.
|
128 |
+
|
129 |
+
```python
|
130 |
+
from setfit import SetFitModel
|
131 |
+
|
132 |
+
# Download from the 🤗 Hub
|
133 |
+
model = SetFitModel.from_pretrained("Varun1010/all-MiniLM-L6-v2-polaris-tiaongBaruPlaza")
|
134 |
+
# Run inference
|
135 |
+
preds = model("Tiong Bahru Plaza, DDC-L20, AHU 20-1 VSD CONTROL")
|
136 |
+
```
|
137 |
+
|
138 |
+
<!--
|
139 |
+
### Downstream Use
|
140 |
+
|
141 |
+
*List how someone could finetune this model on their own dataset.*
|
142 |
+
-->
|
143 |
+
|
144 |
+
<!--
|
145 |
+
### Out-of-Scope Use
|
146 |
+
|
147 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
148 |
+
-->
|
149 |
+
|
150 |
+
<!--
|
151 |
+
## Bias, Risks and Limitations
|
152 |
+
|
153 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
154 |
+
-->
|
155 |
+
|
156 |
+
<!--
|
157 |
+
### Recommendations
|
158 |
+
|
159 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
160 |
+
-->
|
161 |
+
|
162 |
+
## Training Details
|
163 |
+
|
164 |
+
### Training Set Metrics
|
165 |
+
| Training set | Min | Median | Max |
|
166 |
+
|:-------------|:----|:-------|:----|
|
167 |
+
| Word count | 3 | 8.6310 | 12 |
|
168 |
+
|
169 |
+
| Label | Training Sample Count |
|
170 |
+
|:------|:----------------------|
|
171 |
+
| 0 | 2 |
|
172 |
+
| 1 | 2 |
|
173 |
+
| 2 | 2 |
|
174 |
+
| 3 | 2 |
|
175 |
+
| 4 | 2 |
|
176 |
+
| 5 | 2 |
|
177 |
+
| 6 | 2 |
|
178 |
+
| 7 | 2 |
|
179 |
+
| 8 | 2 |
|
180 |
+
| 9 | 2 |
|
181 |
+
| 10 | 2 |
|
182 |
+
| 11 | 2 |
|
183 |
+
| 12 | 2 |
|
184 |
+
| 13 | 2 |
|
185 |
+
| 14 | 2 |
|
186 |
+
| 15 | 2 |
|
187 |
+
| 16 | 2 |
|
188 |
+
| 17 | 2 |
|
189 |
+
| 18 | 2 |
|
190 |
+
| 19 | 2 |
|
191 |
+
| 20 | 2 |
|
192 |
+
| 21 | 2 |
|
193 |
+
| 22 | 2 |
|
194 |
+
| 23 | 1 |
|
195 |
+
| 24 | 1 |
|
196 |
+
| 25 | 2 |
|
197 |
+
| 26 | 2 |
|
198 |
+
| 27 | 2 |
|
199 |
+
| 28 | 2 |
|
200 |
+
| 29 | 2 |
|
201 |
+
| 30 | 2 |
|
202 |
+
| 31 | 2 |
|
203 |
+
| 32 | 2 |
|
204 |
+
| 33 | 2 |
|
205 |
+
| 34 | 2 |
|
206 |
+
| 35 | 2 |
|
207 |
+
| 36 | 2 |
|
208 |
+
| 37 | 2 |
|
209 |
+
| 38 | 2 |
|
210 |
+
| 39 | 2 |
|
211 |
+
| 40 | 1 |
|
212 |
+
| 41 | 1 |
|
213 |
+
| 42 | 2 |
|
214 |
+
| 43 | 2 |
|
215 |
+
|
216 |
+
### Training Hyperparameters
|
217 |
+
- batch_size: (64, 64)
|
218 |
+
- num_epochs: (5, 5)
|
219 |
+
- max_steps: -1
|
220 |
+
- sampling_strategy: oversampling
|
221 |
+
- body_learning_rate: (2e-05, 1e-05)
|
222 |
+
- head_learning_rate: 0.01
|
223 |
+
- loss: CosineSimilarityLoss
|
224 |
+
- distance_metric: cosine_distance
|
225 |
+
- margin: 0.25
|
226 |
+
- end_to_end: False
|
227 |
+
- use_amp: False
|
228 |
+
- warmup_proportion: 0.1
|
229 |
+
- seed: 42
|
230 |
+
- eval_max_steps: -1
|
231 |
+
- load_best_model_at_end: False
|
232 |
+
|
233 |
+
### Training Results
|
234 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
235 |
+
|:------:|:----:|:-------------:|:---------------:|
|
236 |
+
| 0.0093 | 1 | 0.1514 | - |
|
237 |
+
| 0.4630 | 50 | 0.0387 | - |
|
238 |
+
| 0.9259 | 100 | 0.0369 | - |
|
239 |
+
| 1.3889 | 150 | 0.014 | - |
|
240 |
+
| 1.8519 | 200 | 0.0161 | - |
|
241 |
+
| 2.3148 | 250 | 0.018 | - |
|
242 |
+
| 2.7778 | 300 | 0.0181 | - |
|
243 |
+
| 3.2407 | 350 | 0.0156 | - |
|
244 |
+
| 3.7037 | 400 | 0.0145 | - |
|
245 |
+
| 4.1667 | 450 | 0.0186 | - |
|
246 |
+
| 4.6296 | 500 | 0.0124 | - |
|
247 |
+
|
248 |
+
### Framework Versions
|
249 |
+
- Python: 3.10.12
|
250 |
+
- SetFit: 1.0.3
|
251 |
+
- Sentence Transformers: 2.6.1
|
252 |
+
- Transformers: 4.38.2
|
253 |
+
- PyTorch: 2.2.1+cu121
|
254 |
+
- Datasets: 2.18.0
|
255 |
+
- Tokenizers: 0.15.2
|
256 |
+
|
257 |
+
## Citation
|
258 |
+
|
259 |
+
### BibTeX
|
260 |
+
```bibtex
|
261 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
262 |
+
doi = {10.48550/ARXIV.2209.11055},
|
263 |
+
url = {https://arxiv.org/abs/2209.11055},
|
264 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
265 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
266 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
267 |
+
publisher = {arXiv},
|
268 |
+
year = {2022},
|
269 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
270 |
+
}
|
271 |
+
```
|
272 |
+
|
273 |
+
<!--
|
274 |
+
## Glossary
|
275 |
+
|
276 |
+
*Clearly define terms in order to be accessible across audiences.*
|
277 |
+
-->
|
278 |
+
|
279 |
+
<!--
|
280 |
+
## Model Card Authors
|
281 |
+
|
282 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
283 |
+
-->
|
284 |
+
|
285 |
+
<!--
|
286 |
+
## Model Card Contact
|
287 |
+
|
288 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
289 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-MiniLM-L3-v2",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
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": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 3,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"normalize_embeddings": false,
|
3 |
+
"labels": null
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a03d0660bbc5daa570a838824c5e36d31d859b9b0b946a191211f1c8a0cb92d
|
3 |
+
size 69565312
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7fcff36f901583af64ea70f09898044cb6f459c163a9449698d4100550036e5
|
3 |
+
size 136711
|
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": 128,
|
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 |
+
"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 |
+
"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": 128,
|
50 |
+
"model_max_length": 512,
|
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
|
|