Upload folder using huggingface_hub
Browse files- 1_Pooling/config.json +10 -0
- README.md +334 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -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 +56 -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 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- setfit
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- text-classification
|
| 6 |
+
- generated_from_setfit_trainer
|
| 7 |
+
widget:
|
| 8 |
+
- text: 03771 290230 oder 03771 2534030
|
| 9 |
+
- text: Seit Jahresbeginn konnten wieder etliche Praxisbeispiele aus den hessischen
|
| 10 |
+
Regionen für die OloV - Website aufbereitet oder mit aktuellen Entwicklungen ergänzt
|
| 11 |
+
werden.
|
| 12 |
+
- text: 在 Greding 出 口 离 开 A9 高 速 公 路 。
|
| 13 |
+
- text: 'Vortrag : SIMCP WORKSHOP, online ( eingeladen ) ; 16. 11.'
|
| 14 |
+
- text: Nicht nur bei Fragen zur von Smart CROSSBLADE Dachboxen hilft unser neu gestalteter
|
| 15 |
+
weiter.
|
| 16 |
+
metrics:
|
| 17 |
+
- accuracy
|
| 18 |
+
pipeline_tag: text-classification
|
| 19 |
+
library_name: setfit
|
| 20 |
+
inference: false
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# SetFit
|
| 24 |
+
|
| 25 |
+
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.
|
| 26 |
+
|
| 27 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 28 |
+
|
| 29 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 30 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 31 |
+
|
| 32 |
+
## Model Details
|
| 33 |
+
|
| 34 |
+
### Model Description
|
| 35 |
+
- **Model Type:** SetFit
|
| 36 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
| 37 |
+
- **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
|
| 38 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 39 |
+
<!-- - **Number of Classes:** Unknown -->
|
| 40 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 41 |
+
<!-- - **Language:** Unknown -->
|
| 42 |
+
<!-- - **License:** Unknown -->
|
| 43 |
+
|
| 44 |
+
### Model Sources
|
| 45 |
+
|
| 46 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 47 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 48 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 49 |
+
|
| 50 |
+
## Uses
|
| 51 |
+
|
| 52 |
+
### Direct Use for Inference
|
| 53 |
+
|
| 54 |
+
First install the SetFit library:
|
| 55 |
+
|
| 56 |
+
```bash
|
| 57 |
+
pip install setfit
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
Then you can load this model and run inference.
|
| 61 |
+
|
| 62 |
+
```python
|
| 63 |
+
from setfit import SetFitModel
|
| 64 |
+
|
| 65 |
+
# Download from the 🤗 Hub
|
| 66 |
+
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 67 |
+
# Run inference
|
| 68 |
+
preds = model("在 Greding 出 口 离 开 A9 高 速 公 路 。")
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
<!--
|
| 72 |
+
### Downstream Use
|
| 73 |
+
|
| 74 |
+
*List how someone could finetune this model on their own dataset.*
|
| 75 |
+
-->
|
| 76 |
+
|
| 77 |
+
<!--
|
| 78 |
+
### Out-of-Scope Use
|
| 79 |
+
|
| 80 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 81 |
+
-->
|
| 82 |
+
|
| 83 |
+
<!--
|
| 84 |
+
## Bias, Risks and Limitations
|
| 85 |
+
|
| 86 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 87 |
+
-->
|
| 88 |
+
|
| 89 |
+
<!--
|
| 90 |
+
### Recommendations
|
| 91 |
+
|
| 92 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 93 |
+
-->
|
| 94 |
+
|
| 95 |
+
## Training Details
|
| 96 |
+
|
| 97 |
+
### Training Set Metrics
|
| 98 |
+
| Training set | Min | Median | Max |
|
| 99 |
+
|:-------------|:----|:--------|:----|
|
| 100 |
+
| Word count | 1 | 20.4578 | 319 |
|
| 101 |
+
|
| 102 |
+
### Training Hyperparameters
|
| 103 |
+
- batch_size: (8, 8)
|
| 104 |
+
- num_epochs: (1, 16)
|
| 105 |
+
- max_steps: -1
|
| 106 |
+
- sampling_strategy: oversampling
|
| 107 |
+
- body_learning_rate: (2e-05, 1e-05)
|
| 108 |
+
- head_learning_rate: 0.01
|
| 109 |
+
- loss: CoSENTLoss
|
| 110 |
+
- distance_metric: cosine_distance
|
| 111 |
+
- margin: 0.25
|
| 112 |
+
- end_to_end: True
|
| 113 |
+
- use_amp: False
|
| 114 |
+
- warmup_proportion: 0.1
|
| 115 |
+
- l2_weight: 0.01
|
| 116 |
+
- max_length: 512
|
| 117 |
+
- seed: 13579
|
| 118 |
+
- eval_max_steps: -1
|
| 119 |
+
- load_best_model_at_end: False
|
| 120 |
+
|
| 121 |
+
### Training Results
|
| 122 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 123 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
| 124 |
+
| 0.0001 | 1 | 4.5018 | - |
|
| 125 |
+
| 0.0060 | 100 | 5.2045 | - |
|
| 126 |
+
| 0.0119 | 200 | 4.559 | - |
|
| 127 |
+
| 0.0179 | 300 | 3.4579 | - |
|
| 128 |
+
| 0.0239 | 400 | 3.106 | - |
|
| 129 |
+
| 0.0298 | 500 | 2.7464 | - |
|
| 130 |
+
| 0.0358 | 600 | 2.5813 | - |
|
| 131 |
+
| 0.0417 | 700 | 2.5341 | - |
|
| 132 |
+
| 0.0477 | 800 | 2.5279 | - |
|
| 133 |
+
| 0.0537 | 900 | 2.361 | - |
|
| 134 |
+
| 0.0596 | 1000 | 2.2318 | - |
|
| 135 |
+
| 0.0656 | 1100 | 1.8437 | - |
|
| 136 |
+
| 0.0716 | 1200 | 1.6423 | - |
|
| 137 |
+
| 0.0775 | 1300 | 1.7572 | - |
|
| 138 |
+
| 0.0835 | 1400 | 1.8163 | - |
|
| 139 |
+
| 0.0895 | 1500 | 1.4293 | - |
|
| 140 |
+
| 0.0954 | 1600 | 1.3842 | - |
|
| 141 |
+
| 0.1014 | 1700 | 0.9845 | - |
|
| 142 |
+
| 0.1073 | 1800 | 1.0666 | - |
|
| 143 |
+
| 0.1133 | 1900 | 0.6876 | - |
|
| 144 |
+
| 0.1193 | 2000 | 1.4398 | - |
|
| 145 |
+
| 0.1252 | 2100 | 0.7268 | - |
|
| 146 |
+
| 0.1312 | 2200 | 0.7272 | - |
|
| 147 |
+
| 0.1372 | 2300 | 0.9801 | - |
|
| 148 |
+
| 0.1431 | 2400 | 0.6159 | - |
|
| 149 |
+
| 0.1491 | 2500 | 0.465 | - |
|
| 150 |
+
| 0.1551 | 2600 | 1.0453 | - |
|
| 151 |
+
| 0.1610 | 2700 | 0.565 | - |
|
| 152 |
+
| 0.1670 | 2800 | 0.4328 | - |
|
| 153 |
+
| 0.1729 | 2900 | 0.5229 | - |
|
| 154 |
+
| 0.1789 | 3000 | 0.5581 | - |
|
| 155 |
+
| 0.1849 | 3100 | 0.1847 | - |
|
| 156 |
+
| 0.1908 | 3200 | 0.4755 | - |
|
| 157 |
+
| 0.1968 | 3300 | 0.8408 | - |
|
| 158 |
+
| 0.2028 | 3400 | 0.4852 | - |
|
| 159 |
+
| 0.2087 | 3500 | 0.6054 | - |
|
| 160 |
+
| 0.2147 | 3600 | 0.4868 | - |
|
| 161 |
+
| 0.2207 | 3700 | 0.4138 | - |
|
| 162 |
+
| 0.2266 | 3800 | 0.9303 | - |
|
| 163 |
+
| 0.2326 | 3900 | 0.3892 | - |
|
| 164 |
+
| 0.2385 | 4000 | 0.3462 | - |
|
| 165 |
+
| 0.2445 | 4100 | 0.3579 | - |
|
| 166 |
+
| 0.2505 | 4200 | 0.203 | - |
|
| 167 |
+
| 0.2564 | 4300 | 0.4673 | - |
|
| 168 |
+
| 0.2624 | 4400 | 0.1183 | - |
|
| 169 |
+
| 0.2684 | 4500 | 0.506 | - |
|
| 170 |
+
| 0.2743 | 4600 | 0.1378 | - |
|
| 171 |
+
| 0.2803 | 4700 | 0.1603 | - |
|
| 172 |
+
| 0.2863 | 4800 | 0.2337 | - |
|
| 173 |
+
| 0.2922 | 4900 | 0.1526 | - |
|
| 174 |
+
| 0.2982 | 5000 | 0.3597 | - |
|
| 175 |
+
| 0.3042 | 5100 | 0.0672 | - |
|
| 176 |
+
| 0.3101 | 5200 | 0.2134 | - |
|
| 177 |
+
| 0.3161 | 5300 | 0.3521 | - |
|
| 178 |
+
| 0.3220 | 5400 | 0.1098 | - |
|
| 179 |
+
| 0.3280 | 5500 | 0.0723 | - |
|
| 180 |
+
| 0.3340 | 5600 | 0.0349 | - |
|
| 181 |
+
| 0.3399 | 5700 | 0.1389 | - |
|
| 182 |
+
| 0.3459 | 5800 | 0.0966 | - |
|
| 183 |
+
| 0.3519 | 5900 | 0.0998 | - |
|
| 184 |
+
| 0.3578 | 6000 | 0.0263 | - |
|
| 185 |
+
| 0.3638 | 6100 | 0.2343 | - |
|
| 186 |
+
| 0.3698 | 6200 | 0.0776 | - |
|
| 187 |
+
| 0.3757 | 6300 | 0.0037 | - |
|
| 188 |
+
| 0.3817 | 6400 | 0.1324 | - |
|
| 189 |
+
| 0.3876 | 6500 | 0.1259 | - |
|
| 190 |
+
| 0.3936 | 6600 | 0.0197 | - |
|
| 191 |
+
| 0.3996 | 6700 | 0.048 | - |
|
| 192 |
+
| 0.4055 | 6800 | 0.077 | - |
|
| 193 |
+
| 0.4115 | 6900 | 0.025 | - |
|
| 194 |
+
| 0.4175 | 7000 | 0.1416 | - |
|
| 195 |
+
| 0.4234 | 7100 | 0.0622 | - |
|
| 196 |
+
| 0.4294 | 7200 | 0.0625 | - |
|
| 197 |
+
| 0.4354 | 7300 | 0.0281 | - |
|
| 198 |
+
| 0.4413 | 7400 | 0.0308 | - |
|
| 199 |
+
| 0.4473 | 7500 | 0.0675 | - |
|
| 200 |
+
| 0.4532 | 7600 | 0.0551 | - |
|
| 201 |
+
| 0.4592 | 7700 | 0.0174 | - |
|
| 202 |
+
| 0.4652 | 7800 | 0.0719 | - |
|
| 203 |
+
| 0.4711 | 7900 | 0.0426 | - |
|
| 204 |
+
| 0.4771 | 8000 | 0.0231 | - |
|
| 205 |
+
| 0.4831 | 8100 | 0.0253 | - |
|
| 206 |
+
| 0.4890 | 8200 | 0.0106 | - |
|
| 207 |
+
| 0.4950 | 8300 | 0.0199 | - |
|
| 208 |
+
| 0.5010 | 8400 | 0.0181 | - |
|
| 209 |
+
| 0.5069 | 8500 | 0.0136 | - |
|
| 210 |
+
| 0.5129 | 8600 | 0.0378 | - |
|
| 211 |
+
| 0.5188 | 8700 | 0.0151 | - |
|
| 212 |
+
| 0.5248 | 8800 | 0.002 | - |
|
| 213 |
+
| 0.5308 | 8900 | 0.0008 | - |
|
| 214 |
+
| 0.5367 | 9000 | 0.0025 | - |
|
| 215 |
+
| 0.5427 | 9100 | 0.0125 | - |
|
| 216 |
+
| 0.5487 | 9200 | 0.0112 | - |
|
| 217 |
+
| 0.5546 | 9300 | 0.0019 | - |
|
| 218 |
+
| 0.5606 | 9400 | 0.0265 | - |
|
| 219 |
+
| 0.5666 | 9500 | 0.017 | - |
|
| 220 |
+
| 0.5725 | 9600 | 0.0133 | - |
|
| 221 |
+
| 0.5785 | 9700 | 0.0324 | - |
|
| 222 |
+
| 0.5844 | 9800 | 0.0067 | - |
|
| 223 |
+
| 0.5904 | 9900 | 0.0032 | - |
|
| 224 |
+
| 0.5964 | 10000 | 0.0133 | - |
|
| 225 |
+
| 0.6023 | 10100 | 0.0014 | - |
|
| 226 |
+
| 0.6083 | 10200 | 0.0075 | - |
|
| 227 |
+
| 0.6143 | 10300 | 0.0142 | - |
|
| 228 |
+
| 0.6202 | 10400 | 0.0074 | - |
|
| 229 |
+
| 0.6262 | 10500 | 0.0446 | - |
|
| 230 |
+
| 0.6322 | 10600 | 0.0701 | - |
|
| 231 |
+
| 0.6381 | 10700 | 0.0039 | - |
|
| 232 |
+
| 0.6441 | 10800 | 0.0042 | - |
|
| 233 |
+
| 0.6500 | 10900 | 0.004 | - |
|
| 234 |
+
| 0.6560 | 11000 | 0.0009 | - |
|
| 235 |
+
| 0.6620 | 11100 | 0.0007 | - |
|
| 236 |
+
| 0.6679 | 11200 | 0.0012 | - |
|
| 237 |
+
| 0.6739 | 11300 | 0.0178 | - |
|
| 238 |
+
| 0.6799 | 11400 | 0.0024 | - |
|
| 239 |
+
| 0.6858 | 11500 | 0.0006 | - |
|
| 240 |
+
| 0.6918 | 11600 | 0.0011 | - |
|
| 241 |
+
| 0.6978 | 11700 | 0.0043 | - |
|
| 242 |
+
| 0.7037 | 11800 | 0.0013 | - |
|
| 243 |
+
| 0.7097 | 11900 | 0.0019 | - |
|
| 244 |
+
| 0.7156 | 12000 | 0.0025 | - |
|
| 245 |
+
| 0.7216 | 12100 | 0.0004 | - |
|
| 246 |
+
| 0.7276 | 12200 | 0.0065 | - |
|
| 247 |
+
| 0.7335 | 12300 | 0.001 | - |
|
| 248 |
+
| 0.7395 | 12400 | 0.0013 | - |
|
| 249 |
+
| 0.7455 | 12500 | 0.0036 | - |
|
| 250 |
+
| 0.7514 | 12600 | 0.0027 | - |
|
| 251 |
+
| 0.7574 | 12700 | 0.0015 | - |
|
| 252 |
+
| 0.7634 | 12800 | 0.0004 | - |
|
| 253 |
+
| 0.7693 | 12900 | 0.0102 | - |
|
| 254 |
+
| 0.7753 | 13000 | 0.0035 | - |
|
| 255 |
+
| 0.7812 | 13100 | 0.0003 | - |
|
| 256 |
+
| 0.7872 | 13200 | 0.0003 | - |
|
| 257 |
+
| 0.7932 | 13300 | 0.0001 | - |
|
| 258 |
+
| 0.7991 | 13400 | 0.0024 | - |
|
| 259 |
+
| 0.8051 | 13500 | 0.0009 | - |
|
| 260 |
+
| 0.8111 | 13600 | 0.0004 | - |
|
| 261 |
+
| 0.8170 | 13700 | 0.0002 | - |
|
| 262 |
+
| 0.8230 | 13800 | 0.0002 | - |
|
| 263 |
+
| 0.8290 | 13900 | 0.0005 | - |
|
| 264 |
+
| 0.8349 | 14000 | 0.0015 | - |
|
| 265 |
+
| 0.8409 | 14100 | 0.0035 | - |
|
| 266 |
+
| 0.8469 | 14200 | 0.0004 | - |
|
| 267 |
+
| 0.8528 | 14300 | 0.0003 | - |
|
| 268 |
+
| 0.8588 | 14400 | 0.0006 | - |
|
| 269 |
+
| 0.8647 | 14500 | 0.0002 | - |
|
| 270 |
+
| 0.8707 | 14600 | 0.0002 | - |
|
| 271 |
+
| 0.8767 | 14700 | 0.0004 | - |
|
| 272 |
+
| 0.8826 | 14800 | 0.0002 | - |
|
| 273 |
+
| 0.8886 | 14900 | 0.0004 | - |
|
| 274 |
+
| 0.8946 | 15000 | 0.0001 | - |
|
| 275 |
+
| 0.9005 | 15100 | 0.0004 | - |
|
| 276 |
+
| 0.9065 | 15200 | 0.0004 | - |
|
| 277 |
+
| 0.9125 | 15300 | 0.0003 | - |
|
| 278 |
+
| 0.9184 | 15400 | 0.0002 | - |
|
| 279 |
+
| 0.9244 | 15500 | 0.0001 | - |
|
| 280 |
+
| 0.9303 | 15600 | 0.0002 | - |
|
| 281 |
+
| 0.9363 | 15700 | 0.0004 | - |
|
| 282 |
+
| 0.9423 | 15800 | 0.0002 | - |
|
| 283 |
+
| 0.9482 | 15900 | 0.0004 | - |
|
| 284 |
+
| 0.9542 | 16000 | 0.0005 | - |
|
| 285 |
+
| 0.9602 | 16100 | 0.0002 | - |
|
| 286 |
+
| 0.9661 | 16200 | 0.0003 | - |
|
| 287 |
+
| 0.9721 | 16300 | 0.0001 | - |
|
| 288 |
+
| 0.9781 | 16400 | 0.0001 | - |
|
| 289 |
+
| 0.9840 | 16500 | 0.0002 | - |
|
| 290 |
+
| 0.9900 | 16600 | 0.0003 | - |
|
| 291 |
+
| 0.9959 | 16700 | 0.0005 | - |
|
| 292 |
+
|
| 293 |
+
### Framework Versions
|
| 294 |
+
- Python: 3.10.4
|
| 295 |
+
- SetFit: 1.1.2
|
| 296 |
+
- Sentence Transformers: 4.1.0
|
| 297 |
+
- Transformers: 4.52.3
|
| 298 |
+
- PyTorch: 2.7.0+cu126
|
| 299 |
+
- Datasets: 3.6.0
|
| 300 |
+
- Tokenizers: 0.21.1
|
| 301 |
+
|
| 302 |
+
## Citation
|
| 303 |
+
|
| 304 |
+
### BibTeX
|
| 305 |
+
```bibtex
|
| 306 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 307 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 308 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 309 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 310 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 311 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 312 |
+
publisher = {arXiv},
|
| 313 |
+
year = {2022},
|
| 314 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 315 |
+
}
|
| 316 |
+
```
|
| 317 |
+
|
| 318 |
+
<!--
|
| 319 |
+
## Glossary
|
| 320 |
+
|
| 321 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 322 |
+
-->
|
| 323 |
+
|
| 324 |
+
<!--
|
| 325 |
+
## Model Card Authors
|
| 326 |
+
|
| 327 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 328 |
+
-->
|
| 329 |
+
|
| 330 |
+
<!--
|
| 331 |
+
## Model Card Contact
|
| 332 |
+
|
| 333 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 334 |
+
-->
|
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": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.52.3",
|
| 23 |
+
"vocab_size": 119547
|
| 24 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "4.1.0",
|
| 4 |
+
"transformers": "4.52.3",
|
| 5 |
+
"pytorch": "2.7.0+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 sha256:4e213e963400b09ac9ca918a910f08d1092253535d0dbf20dcd9eb21a71977f0
|
| 3 |
+
size 538947416
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f9987dfa2480c2d3617f3e78596ba8d98f7c3717e54b76287cea083f4e89b4d
|
| 3 |
+
size 23056
|
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 |
+
"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": 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
|
|
|