Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +330 -0
- config.json +32 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +20 -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": 768,
|
| 3 |
+
"pooling_mode_cls_token": true,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 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 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: setfit
|
| 3 |
+
metrics:
|
| 4 |
+
- f1
|
| 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: To make introductions between Camelot's Chairman and the Cabinet Secretary.
|
| 14 |
+
We discussed the operation of the UK National Lottery and how to maximise returns
|
| 15 |
+
to National Lottery Good Causes as well as our plans to celebrate the 25th birthday
|
| 16 |
+
of The National Lottery.
|
| 17 |
+
- text: Discussion on crime
|
| 18 |
+
- text: To discuss Northern Powerhouse Rail and HS2
|
| 19 |
+
- text: To discuss food security
|
| 20 |
+
- text: Electricity market
|
| 21 |
+
inference: false
|
| 22 |
+
model-index:
|
| 23 |
+
- name: SetFit
|
| 24 |
+
results:
|
| 25 |
+
- task:
|
| 26 |
+
type: text-classification
|
| 27 |
+
name: Text Classification
|
| 28 |
+
dataset:
|
| 29 |
+
name: Unknown
|
| 30 |
+
type: unknown
|
| 31 |
+
split: test
|
| 32 |
+
metrics:
|
| 33 |
+
- type: f1
|
| 34 |
+
value: 0.8636363636363636
|
| 35 |
+
name: F1
|
| 36 |
+
- type: accuracy
|
| 37 |
+
value: 0.9487179487179487
|
| 38 |
+
name: Accuracy
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
# SetFit
|
| 42 |
+
|
| 43 |
+
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.
|
| 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 |
+
## Model Details
|
| 51 |
+
|
| 52 |
+
### Model Description
|
| 53 |
+
- **Model Type:** SetFit
|
| 54 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
| 55 |
+
- **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
|
| 56 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 57 |
+
<!-- - **Number of Classes:** Unknown -->
|
| 58 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 59 |
+
<!-- - **Language:** Unknown -->
|
| 60 |
+
<!-- - **License:** Unknown -->
|
| 61 |
+
|
| 62 |
+
### Model Sources
|
| 63 |
+
|
| 64 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 65 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 66 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 67 |
+
|
| 68 |
+
## Evaluation
|
| 69 |
+
|
| 70 |
+
### Metrics
|
| 71 |
+
| Label | F1 | Accuracy |
|
| 72 |
+
|:--------|:-------|:---------|
|
| 73 |
+
| **all** | 0.8636 | 0.9487 |
|
| 74 |
+
|
| 75 |
+
## Uses
|
| 76 |
+
|
| 77 |
+
### Direct Use for Inference
|
| 78 |
+
|
| 79 |
+
First install the SetFit library:
|
| 80 |
+
|
| 81 |
+
```bash
|
| 82 |
+
pip install setfit
|
| 83 |
+
```
|
| 84 |
+
|
| 85 |
+
Then you can load this model and run inference.
|
| 86 |
+
|
| 87 |
+
```python
|
| 88 |
+
from setfit import SetFitModel
|
| 89 |
+
|
| 90 |
+
# Download from the 🤗 Hub
|
| 91 |
+
model = SetFitModel.from_pretrained("twright8/setfit-oversample-lobbying")
|
| 92 |
+
# Run inference
|
| 93 |
+
preds = model("Electricity market")
|
| 94 |
+
```
|
| 95 |
+
|
| 96 |
+
<!--
|
| 97 |
+
### Downstream Use
|
| 98 |
+
|
| 99 |
+
*List how someone could finetune this model on their own dataset.*
|
| 100 |
+
-->
|
| 101 |
+
|
| 102 |
+
<!--
|
| 103 |
+
### Out-of-Scope Use
|
| 104 |
+
|
| 105 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 106 |
+
-->
|
| 107 |
+
|
| 108 |
+
<!--
|
| 109 |
+
## Bias, Risks and Limitations
|
| 110 |
+
|
| 111 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 112 |
+
-->
|
| 113 |
+
|
| 114 |
+
<!--
|
| 115 |
+
### Recommendations
|
| 116 |
+
|
| 117 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 118 |
+
-->
|
| 119 |
+
|
| 120 |
+
## Training Details
|
| 121 |
+
|
| 122 |
+
### Training Set Metrics
|
| 123 |
+
| Training set | Min | Median | Max |
|
| 124 |
+
|:-------------|:----|:--------|:----|
|
| 125 |
+
| Word count | 1 | 11.9939 | 117 |
|
| 126 |
+
|
| 127 |
+
### Training Hyperparameters
|
| 128 |
+
- batch_size: (16, 2)
|
| 129 |
+
- num_epochs: (4, 9)
|
| 130 |
+
- max_steps: -1
|
| 131 |
+
- sampling_strategy: oversampling
|
| 132 |
+
- body_learning_rate: (1.0797496673911536e-05, 3.457046714445997e-05)
|
| 133 |
+
- head_learning_rate: 0.0004470582121407239
|
| 134 |
+
- loss: CoSENTLoss
|
| 135 |
+
- distance_metric: cosine_distance
|
| 136 |
+
- margin: 0.25
|
| 137 |
+
- end_to_end: True
|
| 138 |
+
- use_amp: False
|
| 139 |
+
- warmup_proportion: 0.1
|
| 140 |
+
- seed: 42
|
| 141 |
+
- eval_max_steps: -1
|
| 142 |
+
- load_best_model_at_end: True
|
| 143 |
+
|
| 144 |
+
### Training Results
|
| 145 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 146 |
+
|:-------:|:--------:|:-------------:|:---------------:|
|
| 147 |
+
| 0.0006 | 1 | 3.3541 | - |
|
| 148 |
+
| 0.0296 | 50 | 2.9351 | - |
|
| 149 |
+
| 0.0592 | 100 | 3.1966 | - |
|
| 150 |
+
| 0.0888 | 150 | 2.3905 | - |
|
| 151 |
+
| 0.1183 | 200 | 0.0495 | - |
|
| 152 |
+
| 0.1479 | 250 | 0.0118 | - |
|
| 153 |
+
| 0.1775 | 300 | 0.0002 | - |
|
| 154 |
+
| 0.2071 | 350 | 0.0003 | - |
|
| 155 |
+
| 0.2367 | 400 | 0.0161 | - |
|
| 156 |
+
| 0.2663 | 450 | 0.0 | - |
|
| 157 |
+
| 0.2959 | 500 | 0.0001 | - |
|
| 158 |
+
| 0.3254 | 550 | 0.0003 | - |
|
| 159 |
+
| 0.3550 | 600 | 0.0001 | - |
|
| 160 |
+
| 0.3846 | 650 | 0.0 | - |
|
| 161 |
+
| 0.4142 | 700 | 0.0 | - |
|
| 162 |
+
| 0.4438 | 750 | 0.0 | - |
|
| 163 |
+
| 0.4734 | 800 | 0.0 | - |
|
| 164 |
+
| 0.5030 | 850 | 0.0 | - |
|
| 165 |
+
| 0.5325 | 900 | 0.0 | - |
|
| 166 |
+
| 0.5621 | 950 | 0.0 | - |
|
| 167 |
+
| 0.5917 | 1000 | 0.0001 | - |
|
| 168 |
+
| 0.6213 | 1050 | 0.0 | - |
|
| 169 |
+
| 0.6509 | 1100 | 0.0 | - |
|
| 170 |
+
| 0.6805 | 1150 | 0.0 | - |
|
| 171 |
+
| 0.7101 | 1200 | 0.0 | - |
|
| 172 |
+
| 0.7396 | 1250 | 0.0 | - |
|
| 173 |
+
| 0.7692 | 1300 | 0.0 | - |
|
| 174 |
+
| 0.7988 | 1350 | 0.0 | - |
|
| 175 |
+
| 0.8284 | 1400 | 0.0 | - |
|
| 176 |
+
| 0.8580 | 1450 | 0.0 | - |
|
| 177 |
+
| 0.8876 | 1500 | 0.0 | - |
|
| 178 |
+
| 0.9172 | 1550 | 0.0 | - |
|
| 179 |
+
| 0.9467 | 1600 | 0.0 | - |
|
| 180 |
+
| 0.9763 | 1650 | 0.0 | - |
|
| 181 |
+
| **1.0** | **1690** | **-** | **15.2597** |
|
| 182 |
+
| 1.0059 | 1700 | 0.0 | - |
|
| 183 |
+
| 1.0355 | 1750 | 0.0 | - |
|
| 184 |
+
| 1.0651 | 1800 | 0.0 | - |
|
| 185 |
+
| 1.0947 | 1850 | 0.0 | - |
|
| 186 |
+
| 1.1243 | 1900 | 0.0 | - |
|
| 187 |
+
| 1.1538 | 1950 | 0.0 | - |
|
| 188 |
+
| 1.1834 | 2000 | 0.0 | - |
|
| 189 |
+
| 1.2130 | 2050 | 0.0 | - |
|
| 190 |
+
| 1.2426 | 2100 | 0.0 | - |
|
| 191 |
+
| 1.2722 | 2150 | 0.0001 | - |
|
| 192 |
+
| 1.3018 | 2200 | 0.0 | - |
|
| 193 |
+
| 1.3314 | 2250 | 0.0 | - |
|
| 194 |
+
| 1.3609 | 2300 | 0.0 | - |
|
| 195 |
+
| 1.3905 | 2350 | 0.0 | - |
|
| 196 |
+
| 1.4201 | 2400 | 0.0 | - |
|
| 197 |
+
| 1.4497 | 2450 | 0.0 | - |
|
| 198 |
+
| 1.4793 | 2500 | 0.0 | - |
|
| 199 |
+
| 1.5089 | 2550 | 0.0 | - |
|
| 200 |
+
| 1.5385 | 2600 | 0.0 | - |
|
| 201 |
+
| 1.5680 | 2650 | 0.0 | - |
|
| 202 |
+
| 1.5976 | 2700 | 0.0 | - |
|
| 203 |
+
| 1.6272 | 2750 | 0.0 | - |
|
| 204 |
+
| 1.6568 | 2800 | 0.0 | - |
|
| 205 |
+
| 1.6864 | 2850 | 0.0 | - |
|
| 206 |
+
| 1.7160 | 2900 | 0.0 | - |
|
| 207 |
+
| 1.7456 | 2950 | 0.0 | - |
|
| 208 |
+
| 1.7751 | 3000 | 0.0 | - |
|
| 209 |
+
| 1.8047 | 3050 | 0.0001 | - |
|
| 210 |
+
| 1.8343 | 3100 | 0.0 | - |
|
| 211 |
+
| 1.8639 | 3150 | 0.0 | - |
|
| 212 |
+
| 1.8935 | 3200 | 0.0 | - |
|
| 213 |
+
| 1.9231 | 3250 | 0.0 | - |
|
| 214 |
+
| 1.9527 | 3300 | 0.0 | - |
|
| 215 |
+
| 1.9822 | 3350 | 0.0 | - |
|
| 216 |
+
| 2.0 | 3380 | - | 17.8303 |
|
| 217 |
+
| 2.0118 | 3400 | 0.0 | - |
|
| 218 |
+
| 2.0414 | 3450 | 0.0 | - |
|
| 219 |
+
| 2.0710 | 3500 | 0.0 | - |
|
| 220 |
+
| 2.1006 | 3550 | 0.0 | - |
|
| 221 |
+
| 2.1302 | 3600 | 0.0 | - |
|
| 222 |
+
| 2.1598 | 3650 | 0.0 | - |
|
| 223 |
+
| 2.1893 | 3700 | 0.0 | - |
|
| 224 |
+
| 2.2189 | 3750 | 0.0 | - |
|
| 225 |
+
| 2.2485 | 3800 | 0.0 | - |
|
| 226 |
+
| 2.2781 | 3850 | 0.0 | - |
|
| 227 |
+
| 2.3077 | 3900 | 0.0 | - |
|
| 228 |
+
| 2.3373 | 3950 | 0.0 | - |
|
| 229 |
+
| 2.3669 | 4000 | 0.0 | - |
|
| 230 |
+
| 2.3964 | 4050 | 0.0 | - |
|
| 231 |
+
| 2.4260 | 4100 | 0.0 | - |
|
| 232 |
+
| 2.4556 | 4150 | 0.0 | - |
|
| 233 |
+
| 2.4852 | 4200 | 0.0 | - |
|
| 234 |
+
| 2.5148 | 4250 | 0.0 | - |
|
| 235 |
+
| 2.5444 | 4300 | 0.0 | - |
|
| 236 |
+
| 2.5740 | 4350 | 0.0 | - |
|
| 237 |
+
| 2.6036 | 4400 | 0.0 | - |
|
| 238 |
+
| 2.6331 | 4450 | 0.0 | - |
|
| 239 |
+
| 2.6627 | 4500 | 0.0 | - |
|
| 240 |
+
| 2.6923 | 4550 | 0.0 | - |
|
| 241 |
+
| 2.7219 | 4600 | 0.0 | - |
|
| 242 |
+
| 2.7515 | 4650 | 0.0 | - |
|
| 243 |
+
| 2.7811 | 4700 | 0.0 | - |
|
| 244 |
+
| 2.8107 | 4750 | 0.0 | - |
|
| 245 |
+
| 2.8402 | 4800 | 0.0 | - |
|
| 246 |
+
| 2.8698 | 4850 | 0.0 | - |
|
| 247 |
+
| 2.8994 | 4900 | 0.0 | - |
|
| 248 |
+
| 2.9290 | 4950 | 0.0 | - |
|
| 249 |
+
| 2.9586 | 5000 | 0.0 | - |
|
| 250 |
+
| 2.9882 | 5050 | 0.0 | - |
|
| 251 |
+
| 3.0 | 5070 | - | 16.4213 |
|
| 252 |
+
| 3.0178 | 5100 | 0.0 | - |
|
| 253 |
+
| 3.0473 | 5150 | 0.0 | - |
|
| 254 |
+
| 3.0769 | 5200 | 0.0 | - |
|
| 255 |
+
| 3.1065 | 5250 | 0.0 | - |
|
| 256 |
+
| 3.1361 | 5300 | 0.0 | - |
|
| 257 |
+
| 3.1657 | 5350 | 0.0 | - |
|
| 258 |
+
| 3.1953 | 5400 | 0.0 | - |
|
| 259 |
+
| 3.2249 | 5450 | 0.0 | - |
|
| 260 |
+
| 3.2544 | 5500 | 0.0 | - |
|
| 261 |
+
| 3.2840 | 5550 | 0.0 | - |
|
| 262 |
+
| 3.3136 | 5600 | 0.0 | - |
|
| 263 |
+
| 3.3432 | 5650 | 0.0 | - |
|
| 264 |
+
| 3.3728 | 5700 | 0.0 | - |
|
| 265 |
+
| 3.4024 | 5750 | 0.0 | - |
|
| 266 |
+
| 3.4320 | 5800 | 0.0 | - |
|
| 267 |
+
| 3.4615 | 5850 | 0.0 | - |
|
| 268 |
+
| 3.4911 | 5900 | 0.0 | - |
|
| 269 |
+
| 3.5207 | 5950 | 0.0 | - |
|
| 270 |
+
| 3.5503 | 6000 | 0.0 | - |
|
| 271 |
+
| 3.5799 | 6050 | 0.0 | - |
|
| 272 |
+
| 3.6095 | 6100 | 0.0 | - |
|
| 273 |
+
| 3.6391 | 6150 | 0.0 | - |
|
| 274 |
+
| 3.6686 | 6200 | 0.0 | - |
|
| 275 |
+
| 3.6982 | 6250 | 0.0 | - |
|
| 276 |
+
| 3.7278 | 6300 | 0.0 | - |
|
| 277 |
+
| 3.7574 | 6350 | 0.0 | - |
|
| 278 |
+
| 3.7870 | 6400 | 0.0 | - |
|
| 279 |
+
| 3.8166 | 6450 | 0.0 | - |
|
| 280 |
+
| 3.8462 | 6500 | 0.0 | - |
|
| 281 |
+
| 3.8757 | 6550 | 0.0 | - |
|
| 282 |
+
| 3.9053 | 6600 | 0.0 | - |
|
| 283 |
+
| 3.9349 | 6650 | 0.0 | - |
|
| 284 |
+
| 3.9645 | 6700 | 0.0 | - |
|
| 285 |
+
| 3.9941 | 6750 | 0.0 | - |
|
| 286 |
+
| 4.0 | 6760 | - | 16.1196 |
|
| 287 |
+
|
| 288 |
+
* The bold row denotes the saved checkpoint.
|
| 289 |
+
### Framework Versions
|
| 290 |
+
- Python: 3.10.12
|
| 291 |
+
- SetFit: 1.0.3
|
| 292 |
+
- Sentence Transformers: 3.0.1
|
| 293 |
+
- Transformers: 4.39.0
|
| 294 |
+
- PyTorch: 2.3.1+cu118
|
| 295 |
+
- Datasets: 2.20.0
|
| 296 |
+
- Tokenizers: 0.15.2
|
| 297 |
+
|
| 298 |
+
## Citation
|
| 299 |
+
|
| 300 |
+
### BibTeX
|
| 301 |
+
```bibtex
|
| 302 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 303 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 304 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 305 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 306 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 307 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 308 |
+
publisher = {arXiv},
|
| 309 |
+
year = {2022},
|
| 310 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 311 |
+
}
|
| 312 |
+
```
|
| 313 |
+
|
| 314 |
+
<!--
|
| 315 |
+
## Glossary
|
| 316 |
+
|
| 317 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 318 |
+
-->
|
| 319 |
+
|
| 320 |
+
<!--
|
| 321 |
+
## Model Card Authors
|
| 322 |
+
|
| 323 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 324 |
+
-->
|
| 325 |
+
|
| 326 |
+
<!--
|
| 327 |
+
## Model Card Contact
|
| 328 |
+
|
| 329 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 330 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/step_1690",
|
| 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": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.39.0",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.39.0",
|
| 5 |
+
"pytorch": "2.3.1+cu118"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
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 sha256:6dd367b368396265de63b19c53b7242a106e647be88696a715853359c7429621
|
| 3 |
+
size 437951328
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ddef8f387576766559a4f2fc6cbb363419a023dbc9f358e2f917f8bbe69644
|
| 3 |
+
size 13858
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": true
|
| 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": 512,
|
| 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
|
|
|