Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +521 -0
- config.json +25 -0
- config_sentence_transformers.json +14 -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 +65 -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 +1,521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- setfit
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- text-classification
|
| 6 |
+
- generated_from_setfit_trainer
|
| 7 |
+
widget:
|
| 8 |
+
- text: The TCS software shall have an open architecture and be capable of being hosted
|
| 9 |
+
on computers that are typically supported by the using Service.
|
| 10 |
+
- text: 3 It shall be possible to deregister up to ten functional numbers to items
|
| 11 |
+
of equipment physically connected to the Cab radio within 30 seconds. (M)
|
| 12 |
+
- text: 1 The EIRENE system shall enable users to originate and receive calls by functional
|
| 13 |
+
number. (M)
|
| 14 |
+
- text: The product shall store new conference rooms.
|
| 15 |
+
- text: Before authomatic transition to Shunting, ETCS shall request confirmation
|
| 16 |
+
from the driver.
|
| 17 |
+
metrics:
|
| 18 |
+
- micro_f1
|
| 19 |
+
- macro_f1
|
| 20 |
+
- hamming_accuracy
|
| 21 |
+
- subset_accuracy
|
| 22 |
+
pipeline_tag: text-classification
|
| 23 |
+
library_name: setfit
|
| 24 |
+
inference: true
|
| 25 |
+
model-index:
|
| 26 |
+
- name: SetFit
|
| 27 |
+
results:
|
| 28 |
+
- task:
|
| 29 |
+
type: text-classification
|
| 30 |
+
name: Text Classification
|
| 31 |
+
dataset:
|
| 32 |
+
name: Unknown
|
| 33 |
+
type: unknown
|
| 34 |
+
split: test
|
| 35 |
+
metrics:
|
| 36 |
+
- type: micro_f1
|
| 37 |
+
value: 0.5705128205128205
|
| 38 |
+
name: Micro_F1
|
| 39 |
+
- type: macro_f1
|
| 40 |
+
value: 0.5793040286957435
|
| 41 |
+
name: Macro_F1
|
| 42 |
+
- type: hamming_accuracy
|
| 43 |
+
value: 0.8897119341563786
|
| 44 |
+
name: Hamming_Accuracy
|
| 45 |
+
- type: subset_accuracy
|
| 46 |
+
value: 0.5720164609053497
|
| 47 |
+
name: Subset_Accuracy
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
# SetFit
|
| 51 |
+
|
| 52 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A WeightedBinaryRelevanceHead instance is used for classification.
|
| 53 |
+
|
| 54 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 55 |
+
|
| 56 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 57 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 58 |
+
|
| 59 |
+
## Model Details
|
| 60 |
+
|
| 61 |
+
### Model Description
|
| 62 |
+
- **Model Type:** SetFit
|
| 63 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
| 64 |
+
- **Classification head:** a WeightedBinaryRelevanceHead instance
|
| 65 |
+
- **Maximum Sequence Length:** 256 tokens
|
| 66 |
+
<!-- - **Number of Classes:** Unknown -->
|
| 67 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 68 |
+
<!-- - **Language:** Unknown -->
|
| 69 |
+
<!-- - **License:** Unknown -->
|
| 70 |
+
|
| 71 |
+
### Model Sources
|
| 72 |
+
|
| 73 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 74 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 75 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 76 |
+
|
| 77 |
+
## Evaluation
|
| 78 |
+
|
| 79 |
+
### Metrics
|
| 80 |
+
| Label | Micro_F1 | Macro_F1 | Hamming_Accuracy | Subset_Accuracy |
|
| 81 |
+
|:--------|:---------|:---------|:-----------------|:----------------|
|
| 82 |
+
| **all** | 0.5705 | 0.5793 | 0.8897 | 0.5720 |
|
| 83 |
+
|
| 84 |
+
## Uses
|
| 85 |
+
|
| 86 |
+
### Direct Use for Inference
|
| 87 |
+
|
| 88 |
+
First install the SetFit library:
|
| 89 |
+
|
| 90 |
+
```bash
|
| 91 |
+
pip install setfit
|
| 92 |
+
```
|
| 93 |
+
|
| 94 |
+
Then you can load this model and run inference.
|
| 95 |
+
|
| 96 |
+
```python
|
| 97 |
+
from setfit import SetFitModel
|
| 98 |
+
|
| 99 |
+
# Download from the 🤗 Hub
|
| 100 |
+
model = SetFitModel.from_pretrained("Hulyyy/req-quality-setfit-128")
|
| 101 |
+
# Run inference
|
| 102 |
+
preds = model("The product shall store new conference rooms.")
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
<!--
|
| 106 |
+
### Downstream Use
|
| 107 |
+
|
| 108 |
+
*List how someone could finetune this model on their own dataset.*
|
| 109 |
+
-->
|
| 110 |
+
|
| 111 |
+
<!--
|
| 112 |
+
### Out-of-Scope Use
|
| 113 |
+
|
| 114 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 115 |
+
-->
|
| 116 |
+
|
| 117 |
+
<!--
|
| 118 |
+
## Bias, Risks and Limitations
|
| 119 |
+
|
| 120 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 121 |
+
-->
|
| 122 |
+
|
| 123 |
+
<!--
|
| 124 |
+
### Recommendations
|
| 125 |
+
|
| 126 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 127 |
+
-->
|
| 128 |
+
|
| 129 |
+
## Training Details
|
| 130 |
+
|
| 131 |
+
### Training Set Metrics
|
| 132 |
+
| Training set | Min | Median | Max |
|
| 133 |
+
|:-------------|:----|:--------|:----|
|
| 134 |
+
| Word count | 2 | 19.3840 | 32 |
|
| 135 |
+
|
| 136 |
+
### Training Hyperparameters
|
| 137 |
+
- batch_size: (64, 64)
|
| 138 |
+
- num_epochs: (3, 3)
|
| 139 |
+
- max_steps: -1
|
| 140 |
+
- sampling_strategy: oversampling
|
| 141 |
+
- num_iterations: 150
|
| 142 |
+
- body_learning_rate: (1e-05, 1e-05)
|
| 143 |
+
- head_learning_rate: 1e-05
|
| 144 |
+
- loss: CosineSimilarityLoss
|
| 145 |
+
- distance_metric: cosine_distance
|
| 146 |
+
- margin: 0.25
|
| 147 |
+
- end_to_end: False
|
| 148 |
+
- use_amp: True
|
| 149 |
+
- warmup_proportion: 0.1
|
| 150 |
+
- l2_weight: 0.01
|
| 151 |
+
- seed: 42
|
| 152 |
+
- eval_max_steps: -1
|
| 153 |
+
- load_best_model_at_end: False
|
| 154 |
+
|
| 155 |
+
### Training Results
|
| 156 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 157 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
| 158 |
+
| 0.0002 | 1 | 0.3465 | - |
|
| 159 |
+
| 0.0094 | 50 | 0.3586 | - |
|
| 160 |
+
| 0.0187 | 100 | 0.3442 | - |
|
| 161 |
+
| 0.0281 | 150 | 0.3214 | - |
|
| 162 |
+
| 0.0375 | 200 | 0.2907 | - |
|
| 163 |
+
| 0.0469 | 250 | 0.2647 | - |
|
| 164 |
+
| 0.0562 | 300 | 0.2612 | - |
|
| 165 |
+
| 0.0656 | 350 | 0.2543 | - |
|
| 166 |
+
| 0.0750 | 400 | 0.2507 | - |
|
| 167 |
+
| 0.0843 | 450 | 0.2483 | - |
|
| 168 |
+
| 0.0937 | 500 | 0.2435 | - |
|
| 169 |
+
| 0.1031 | 550 | 0.2409 | - |
|
| 170 |
+
| 0.1125 | 600 | 0.2329 | - |
|
| 171 |
+
| 0.1218 | 650 | 0.2318 | - |
|
| 172 |
+
| 0.1312 | 700 | 0.2292 | - |
|
| 173 |
+
| 0.1406 | 750 | 0.226 | - |
|
| 174 |
+
| 0.1500 | 800 | 0.2194 | - |
|
| 175 |
+
| 0.1593 | 850 | 0.2184 | - |
|
| 176 |
+
| 0.1687 | 900 | 0.2135 | - |
|
| 177 |
+
| 0.1781 | 950 | 0.2133 | - |
|
| 178 |
+
| 0.1874 | 1000 | 0.2052 | - |
|
| 179 |
+
| 0.1968 | 1050 | 0.2019 | - |
|
| 180 |
+
| 0.2062 | 1100 | 0.1977 | - |
|
| 181 |
+
| 0.2156 | 1150 | 0.196 | - |
|
| 182 |
+
| 0.2249 | 1200 | 0.185 | - |
|
| 183 |
+
| 0.2343 | 1250 | 0.1812 | - |
|
| 184 |
+
| 0.2437 | 1300 | 0.1747 | - |
|
| 185 |
+
| 0.2530 | 1350 | 0.1756 | - |
|
| 186 |
+
| 0.2624 | 1400 | 0.1634 | - |
|
| 187 |
+
| 0.2718 | 1450 | 0.158 | - |
|
| 188 |
+
| 0.2812 | 1500 | 0.1502 | - |
|
| 189 |
+
| 0.2905 | 1550 | 0.1433 | - |
|
| 190 |
+
| 0.2999 | 1600 | 0.1305 | - |
|
| 191 |
+
| 0.3093 | 1650 | 0.1333 | - |
|
| 192 |
+
| 0.3187 | 1700 | 0.1115 | - |
|
| 193 |
+
| 0.3280 | 1750 | 0.1073 | - |
|
| 194 |
+
| 0.3374 | 1800 | 0.1016 | - |
|
| 195 |
+
| 0.3468 | 1850 | 0.0978 | - |
|
| 196 |
+
| 0.3561 | 1900 | 0.0861 | - |
|
| 197 |
+
| 0.3655 | 1950 | 0.0767 | - |
|
| 198 |
+
| 0.3749 | 2000 | 0.0733 | - |
|
| 199 |
+
| 0.3843 | 2050 | 0.0676 | - |
|
| 200 |
+
| 0.3936 | 2100 | 0.061 | - |
|
| 201 |
+
| 0.4030 | 2150 | 0.0594 | - |
|
| 202 |
+
| 0.4124 | 2200 | 0.0575 | - |
|
| 203 |
+
| 0.4217 | 2250 | 0.0526 | - |
|
| 204 |
+
| 0.4311 | 2300 | 0.0484 | - |
|
| 205 |
+
| 0.4405 | 2350 | 0.043 | - |
|
| 206 |
+
| 0.4499 | 2400 | 0.0424 | - |
|
| 207 |
+
| 0.4592 | 2450 | 0.0396 | - |
|
| 208 |
+
| 0.4686 | 2500 | 0.0435 | - |
|
| 209 |
+
| 0.4780 | 2550 | 0.0361 | - |
|
| 210 |
+
| 0.4873 | 2600 | 0.0354 | - |
|
| 211 |
+
| 0.4967 | 2650 | 0.0372 | - |
|
| 212 |
+
| 0.5061 | 2700 | 0.0342 | - |
|
| 213 |
+
| 0.5155 | 2750 | 0.0342 | - |
|
| 214 |
+
| 0.5248 | 2800 | 0.0314 | - |
|
| 215 |
+
| 0.5342 | 2850 | 0.0296 | - |
|
| 216 |
+
| 0.5436 | 2900 | 0.0316 | - |
|
| 217 |
+
| 0.5530 | 2950 | 0.0295 | - |
|
| 218 |
+
| 0.5623 | 3000 | 0.0271 | - |
|
| 219 |
+
| 0.5717 | 3050 | 0.0278 | - |
|
| 220 |
+
| 0.5811 | 3100 | 0.0293 | - |
|
| 221 |
+
| 0.5904 | 3150 | 0.025 | - |
|
| 222 |
+
| 0.5998 | 3200 | 0.024 | - |
|
| 223 |
+
| 0.6092 | 3250 | 0.0233 | - |
|
| 224 |
+
| 0.6186 | 3300 | 0.0237 | - |
|
| 225 |
+
| 0.6279 | 3350 | 0.0249 | - |
|
| 226 |
+
| 0.6373 | 3400 | 0.0228 | - |
|
| 227 |
+
| 0.6467 | 3450 | 0.0265 | - |
|
| 228 |
+
| 0.6560 | 3500 | 0.0208 | - |
|
| 229 |
+
| 0.6654 | 3550 | 0.0249 | - |
|
| 230 |
+
| 0.6748 | 3600 | 0.0241 | - |
|
| 231 |
+
| 0.6842 | 3650 | 0.0211 | - |
|
| 232 |
+
| 0.6935 | 3700 | 0.0202 | - |
|
| 233 |
+
| 0.7029 | 3750 | 0.0212 | - |
|
| 234 |
+
| 0.7123 | 3800 | 0.0203 | - |
|
| 235 |
+
| 0.7216 | 3850 | 0.0206 | - |
|
| 236 |
+
| 0.7310 | 3900 | 0.0188 | - |
|
| 237 |
+
| 0.7404 | 3950 | 0.0192 | - |
|
| 238 |
+
| 0.7498 | 4000 | 0.0193 | - |
|
| 239 |
+
| 0.7591 | 4050 | 0.0182 | - |
|
| 240 |
+
| 0.7685 | 4100 | 0.0177 | - |
|
| 241 |
+
| 0.7779 | 4150 | 0.0154 | - |
|
| 242 |
+
| 0.7873 | 4200 | 0.0147 | - |
|
| 243 |
+
| 0.7966 | 4250 | 0.0148 | - |
|
| 244 |
+
| 0.8060 | 4300 | 0.0139 | - |
|
| 245 |
+
| 0.8154 | 4350 | 0.0129 | - |
|
| 246 |
+
| 0.8247 | 4400 | 0.0125 | - |
|
| 247 |
+
| 0.8341 | 4450 | 0.0123 | - |
|
| 248 |
+
| 0.8435 | 4500 | 0.0112 | - |
|
| 249 |
+
| 0.8529 | 4550 | 0.0104 | - |
|
| 250 |
+
| 0.8622 | 4600 | 0.0107 | - |
|
| 251 |
+
| 0.8716 | 4650 | 0.0097 | - |
|
| 252 |
+
| 0.8810 | 4700 | 0.0101 | - |
|
| 253 |
+
| 0.8903 | 4750 | 0.0112 | - |
|
| 254 |
+
| 0.8997 | 4800 | 0.0088 | - |
|
| 255 |
+
| 0.9091 | 4850 | 0.0085 | - |
|
| 256 |
+
| 0.9185 | 4900 | 0.0086 | - |
|
| 257 |
+
| 0.9278 | 4950 | 0.0105 | - |
|
| 258 |
+
| 0.9372 | 5000 | 0.0089 | - |
|
| 259 |
+
| 0.9466 | 5050 | 0.0069 | - |
|
| 260 |
+
| 0.9560 | 5100 | 0.0084 | - |
|
| 261 |
+
| 0.9653 | 5150 | 0.0081 | - |
|
| 262 |
+
| 0.9747 | 5200 | 0.008 | - |
|
| 263 |
+
| 0.9841 | 5250 | 0.0077 | - |
|
| 264 |
+
| 0.9934 | 5300 | 0.0086 | - |
|
| 265 |
+
| 1.0028 | 5350 | 0.0069 | - |
|
| 266 |
+
| 1.0122 | 5400 | 0.0059 | - |
|
| 267 |
+
| 1.0216 | 5450 | 0.0062 | - |
|
| 268 |
+
| 1.0309 | 5500 | 0.0063 | - |
|
| 269 |
+
| 1.0403 | 5550 | 0.0065 | - |
|
| 270 |
+
| 1.0497 | 5600 | 0.0072 | - |
|
| 271 |
+
| 1.0590 | 5650 | 0.0063 | - |
|
| 272 |
+
| 1.0684 | 5700 | 0.0066 | - |
|
| 273 |
+
| 1.0778 | 5750 | 0.0068 | - |
|
| 274 |
+
| 1.0872 | 5800 | 0.0058 | - |
|
| 275 |
+
| 1.0965 | 5850 | 0.0056 | - |
|
| 276 |
+
| 1.1059 | 5900 | 0.0043 | - |
|
| 277 |
+
| 1.1153 | 5950 | 0.0053 | - |
|
| 278 |
+
| 1.1246 | 6000 | 0.0061 | - |
|
| 279 |
+
| 1.1340 | 6050 | 0.0053 | - |
|
| 280 |
+
| 1.1434 | 6100 | 0.0057 | - |
|
| 281 |
+
| 1.1528 | 6150 | 0.004 | - |
|
| 282 |
+
| 1.1621 | 6200 | 0.0052 | - |
|
| 283 |
+
| 1.1715 | 6250 | 0.0048 | - |
|
| 284 |
+
| 1.1809 | 6300 | 0.0055 | - |
|
| 285 |
+
| 1.1903 | 6350 | 0.0054 | - |
|
| 286 |
+
| 1.1996 | 6400 | 0.0057 | - |
|
| 287 |
+
| 1.2090 | 6450 | 0.0053 | - |
|
| 288 |
+
| 1.2184 | 6500 | 0.0044 | - |
|
| 289 |
+
| 1.2277 | 6550 | 0.0057 | - |
|
| 290 |
+
| 1.2371 | 6600 | 0.004 | - |
|
| 291 |
+
| 1.2465 | 6650 | 0.0054 | - |
|
| 292 |
+
| 1.2559 | 6700 | 0.0056 | - |
|
| 293 |
+
| 1.2652 | 6750 | 0.0044 | - |
|
| 294 |
+
| 1.2746 | 6800 | 0.004 | - |
|
| 295 |
+
| 1.2840 | 6850 | 0.0045 | - |
|
| 296 |
+
| 1.2933 | 6900 | 0.0051 | - |
|
| 297 |
+
| 1.3027 | 6950 | 0.0052 | - |
|
| 298 |
+
| 1.3121 | 7000 | 0.0043 | - |
|
| 299 |
+
| 1.3215 | 7050 | 0.0037 | - |
|
| 300 |
+
| 1.3308 | 7100 | 0.004 | - |
|
| 301 |
+
| 1.3402 | 7150 | 0.004 | - |
|
| 302 |
+
| 1.3496 | 7200 | 0.0043 | - |
|
| 303 |
+
| 1.3590 | 7250 | 0.004 | - |
|
| 304 |
+
| 1.3683 | 7300 | 0.0041 | - |
|
| 305 |
+
| 1.3777 | 7350 | 0.0049 | - |
|
| 306 |
+
| 1.3871 | 7400 | 0.0032 | - |
|
| 307 |
+
| 1.3964 | 7450 | 0.0037 | - |
|
| 308 |
+
| 1.4058 | 7500 | 0.0039 | - |
|
| 309 |
+
| 1.4152 | 7550 | 0.0035 | - |
|
| 310 |
+
| 1.4246 | 7600 | 0.0031 | - |
|
| 311 |
+
| 1.4339 | 7650 | 0.0032 | - |
|
| 312 |
+
| 1.4433 | 7700 | 0.0033 | - |
|
| 313 |
+
| 1.4527 | 7750 | 0.0037 | - |
|
| 314 |
+
| 1.4620 | 7800 | 0.004 | - |
|
| 315 |
+
| 1.4714 | 7850 | 0.0027 | - |
|
| 316 |
+
| 1.4808 | 7900 | 0.0035 | - |
|
| 317 |
+
| 1.4902 | 7950 | 0.0026 | - |
|
| 318 |
+
| 1.4995 | 8000 | 0.0031 | - |
|
| 319 |
+
| 1.5089 | 8050 | 0.0027 | - |
|
| 320 |
+
| 1.5183 | 8100 | 0.0033 | - |
|
| 321 |
+
| 1.5276 | 8150 | 0.0029 | - |
|
| 322 |
+
| 1.5370 | 8200 | 0.003 | - |
|
| 323 |
+
| 1.5464 | 8250 | 0.0031 | - |
|
| 324 |
+
| 1.5558 | 8300 | 0.0025 | - |
|
| 325 |
+
| 1.5651 | 8350 | 0.0026 | - |
|
| 326 |
+
| 1.5745 | 8400 | 0.0031 | - |
|
| 327 |
+
| 1.5839 | 8450 | 0.0026 | - |
|
| 328 |
+
| 1.5933 | 8500 | 0.0027 | - |
|
| 329 |
+
| 1.6026 | 8550 | 0.0026 | - |
|
| 330 |
+
| 1.6120 | 8600 | 0.0025 | - |
|
| 331 |
+
| 1.6214 | 8650 | 0.0024 | - |
|
| 332 |
+
| 1.6307 | 8700 | 0.0026 | - |
|
| 333 |
+
| 1.6401 | 8750 | 0.0022 | - |
|
| 334 |
+
| 1.6495 | 8800 | 0.0023 | - |
|
| 335 |
+
| 1.6589 | 8850 | 0.0023 | - |
|
| 336 |
+
| 1.6682 | 8900 | 0.0023 | - |
|
| 337 |
+
| 1.6776 | 8950 | 0.0026 | - |
|
| 338 |
+
| 1.6870 | 9000 | 0.0022 | - |
|
| 339 |
+
| 1.6963 | 9050 | 0.0022 | - |
|
| 340 |
+
| 1.7057 | 9100 | 0.0017 | - |
|
| 341 |
+
| 1.7151 | 9150 | 0.0022 | - |
|
| 342 |
+
| 1.7245 | 9200 | 0.0029 | - |
|
| 343 |
+
| 1.7338 | 9250 | 0.0018 | - |
|
| 344 |
+
| 1.7432 | 9300 | 0.0024 | - |
|
| 345 |
+
| 1.7526 | 9350 | 0.0024 | - |
|
| 346 |
+
| 1.7619 | 9400 | 0.0021 | - |
|
| 347 |
+
| 1.7713 | 9450 | 0.0022 | - |
|
| 348 |
+
| 1.7807 | 9500 | 0.0019 | - |
|
| 349 |
+
| 1.7901 | 9550 | 0.0019 | - |
|
| 350 |
+
| 1.7994 | 9600 | 0.0018 | - |
|
| 351 |
+
| 1.8088 | 9650 | 0.0022 | - |
|
| 352 |
+
| 1.8182 | 9700 | 0.0018 | - |
|
| 353 |
+
| 1.8276 | 9750 | 0.0019 | - |
|
| 354 |
+
| 1.8369 | 9800 | 0.0018 | - |
|
| 355 |
+
| 1.8463 | 9850 | 0.0012 | - |
|
| 356 |
+
| 1.8557 | 9900 | 0.0016 | - |
|
| 357 |
+
| 1.8650 | 9950 | 0.0019 | - |
|
| 358 |
+
| 1.8744 | 10000 | 0.0015 | - |
|
| 359 |
+
| 1.8838 | 10050 | 0.0019 | - |
|
| 360 |
+
| 1.8932 | 10100 | 0.0014 | - |
|
| 361 |
+
| 1.9025 | 10150 | 0.0016 | - |
|
| 362 |
+
| 1.9119 | 10200 | 0.0019 | - |
|
| 363 |
+
| 1.9213 | 10250 | 0.0018 | - |
|
| 364 |
+
| 1.9306 | 10300 | 0.0012 | - |
|
| 365 |
+
| 1.9400 | 10350 | 0.0015 | - |
|
| 366 |
+
| 1.9494 | 10400 | 0.0017 | - |
|
| 367 |
+
| 1.9588 | 10450 | 0.0015 | - |
|
| 368 |
+
| 1.9681 | 10500 | 0.0015 | - |
|
| 369 |
+
| 1.9775 | 10550 | 0.0019 | - |
|
| 370 |
+
| 1.9869 | 10600 | 0.0018 | - |
|
| 371 |
+
| 1.9963 | 10650 | 0.0014 | - |
|
| 372 |
+
| 2.0056 | 10700 | 0.0015 | - |
|
| 373 |
+
| 2.0150 | 10750 | 0.0011 | - |
|
| 374 |
+
| 2.0244 | 10800 | 0.0014 | - |
|
| 375 |
+
| 2.0337 | 10850 | 0.0014 | - |
|
| 376 |
+
| 2.0431 | 10900 | 0.0014 | - |
|
| 377 |
+
| 2.0525 | 10950 | 0.0017 | - |
|
| 378 |
+
| 2.0619 | 11000 | 0.0014 | - |
|
| 379 |
+
| 2.0712 | 11050 | 0.0015 | - |
|
| 380 |
+
| 2.0806 | 11100 | 0.0013 | - |
|
| 381 |
+
| 2.0900 | 11150 | 0.001 | - |
|
| 382 |
+
| 2.0993 | 11200 | 0.0016 | - |
|
| 383 |
+
| 2.1087 | 11250 | 0.0015 | - |
|
| 384 |
+
| 2.1181 | 11300 | 0.0015 | - |
|
| 385 |
+
| 2.1275 | 11350 | 0.001 | - |
|
| 386 |
+
| 2.1368 | 11400 | 0.0017 | - |
|
| 387 |
+
| 2.1462 | 11450 | 0.0014 | - |
|
| 388 |
+
| 2.1556 | 11500 | 0.0012 | - |
|
| 389 |
+
| 2.1649 | 11550 | 0.0013 | - |
|
| 390 |
+
| 2.1743 | 11600 | 0.0011 | - |
|
| 391 |
+
| 2.1837 | 11650 | 0.0013 | - |
|
| 392 |
+
| 2.1931 | 11700 | 0.001 | - |
|
| 393 |
+
| 2.2024 | 11750 | 0.0013 | - |
|
| 394 |
+
| 2.2118 | 11800 | 0.0012 | - |
|
| 395 |
+
| 2.2212 | 11850 | 0.0011 | - |
|
| 396 |
+
| 2.2306 | 11900 | 0.0014 | - |
|
| 397 |
+
| 2.2399 | 11950 | 0.001 | - |
|
| 398 |
+
| 2.2493 | 12000 | 0.0015 | - |
|
| 399 |
+
| 2.2587 | 12050 | 0.0012 | - |
|
| 400 |
+
| 2.2680 | 12100 | 0.0011 | - |
|
| 401 |
+
| 2.2774 | 12150 | 0.0007 | - |
|
| 402 |
+
| 2.2868 | 12200 | 0.0011 | - |
|
| 403 |
+
| 2.2962 | 12250 | 0.0015 | - |
|
| 404 |
+
| 2.3055 | 12300 | 0.0011 | - |
|
| 405 |
+
| 2.3149 | 12350 | 0.0011 | - |
|
| 406 |
+
| 2.3243 | 12400 | 0.0012 | - |
|
| 407 |
+
| 2.3336 | 12450 | 0.0009 | - |
|
| 408 |
+
| 2.3430 | 12500 | 0.0009 | - |
|
| 409 |
+
| 2.3524 | 12550 | 0.0012 | - |
|
| 410 |
+
| 2.3618 | 12600 | 0.0012 | - |
|
| 411 |
+
| 2.3711 | 12650 | 0.0012 | - |
|
| 412 |
+
| 2.3805 | 12700 | 0.0008 | - |
|
| 413 |
+
| 2.3899 | 12750 | 0.0012 | - |
|
| 414 |
+
| 2.3993 | 12800 | 0.0009 | - |
|
| 415 |
+
| 2.4086 | 12850 | 0.0011 | - |
|
| 416 |
+
| 2.4180 | 12900 | 0.0013 | - |
|
| 417 |
+
| 2.4274 | 12950 | 0.0006 | - |
|
| 418 |
+
| 2.4367 | 13000 | 0.0006 | - |
|
| 419 |
+
| 2.4461 | 13050 | 0.001 | - |
|
| 420 |
+
| 2.4555 | 13100 | 0.0011 | - |
|
| 421 |
+
| 2.4649 | 13150 | 0.0007 | - |
|
| 422 |
+
| 2.4742 | 13200 | 0.0009 | - |
|
| 423 |
+
| 2.4836 | 13250 | 0.001 | - |
|
| 424 |
+
| 2.4930 | 13300 | 0.0007 | - |
|
| 425 |
+
| 2.5023 | 13350 | 0.0012 | - |
|
| 426 |
+
| 2.5117 | 13400 | 0.001 | - |
|
| 427 |
+
| 2.5211 | 13450 | 0.0009 | - |
|
| 428 |
+
| 2.5305 | 13500 | 0.001 | - |
|
| 429 |
+
| 2.5398 | 13550 | 0.0008 | - |
|
| 430 |
+
| 2.5492 | 13600 | 0.001 | - |
|
| 431 |
+
| 2.5586 | 13650 | 0.0012 | - |
|
| 432 |
+
| 2.5679 | 13700 | 0.0009 | - |
|
| 433 |
+
| 2.5773 | 13750 | 0.0007 | - |
|
| 434 |
+
| 2.5867 | 13800 | 0.0006 | - |
|
| 435 |
+
| 2.5961 | 13850 | 0.0007 | - |
|
| 436 |
+
| 2.6054 | 13900 | 0.0006 | - |
|
| 437 |
+
| 2.6148 | 13950 | 0.0013 | - |
|
| 438 |
+
| 2.6242 | 14000 | 0.0008 | - |
|
| 439 |
+
| 2.6336 | 14050 | 0.0012 | - |
|
| 440 |
+
| 2.6429 | 14100 | 0.0008 | - |
|
| 441 |
+
| 2.6523 | 14150 | 0.0008 | - |
|
| 442 |
+
| 2.6617 | 14200 | 0.001 | - |
|
| 443 |
+
| 2.6710 | 14250 | 0.0008 | - |
|
| 444 |
+
| 2.6804 | 14300 | 0.0008 | - |
|
| 445 |
+
| 2.6898 | 14350 | 0.0008 | - |
|
| 446 |
+
| 2.6992 | 14400 | 0.0008 | - |
|
| 447 |
+
| 2.7085 | 14450 | 0.0011 | - |
|
| 448 |
+
| 2.7179 | 14500 | 0.001 | - |
|
| 449 |
+
| 2.7273 | 14550 | 0.0012 | - |
|
| 450 |
+
| 2.7366 | 14600 | 0.0012 | - |
|
| 451 |
+
| 2.7460 | 14650 | 0.0009 | - |
|
| 452 |
+
| 2.7554 | 14700 | 0.0008 | - |
|
| 453 |
+
| 2.7648 | 14750 | 0.0012 | - |
|
| 454 |
+
| 2.7741 | 14800 | 0.0008 | - |
|
| 455 |
+
| 2.7835 | 14850 | 0.0011 | - |
|
| 456 |
+
| 2.7929 | 14900 | 0.0009 | - |
|
| 457 |
+
| 2.8022 | 14950 | 0.0011 | - |
|
| 458 |
+
| 2.8116 | 15000 | 0.0009 | - |
|
| 459 |
+
| 2.8210 | 15050 | 0.0011 | - |
|
| 460 |
+
| 2.8304 | 15100 | 0.0009 | - |
|
| 461 |
+
| 2.8397 | 15150 | 0.0009 | - |
|
| 462 |
+
| 2.8491 | 15200 | 0.0008 | - |
|
| 463 |
+
| 2.8585 | 15250 | 0.0013 | - |
|
| 464 |
+
| 2.8679 | 15300 | 0.0011 | - |
|
| 465 |
+
| 2.8772 | 15350 | 0.0008 | - |
|
| 466 |
+
| 2.8866 | 15400 | 0.0006 | - |
|
| 467 |
+
| 2.8960 | 15450 | 0.0008 | - |
|
| 468 |
+
| 2.9053 | 15500 | 0.0009 | - |
|
| 469 |
+
| 2.9147 | 15550 | 0.0009 | - |
|
| 470 |
+
| 2.9241 | 15600 | 0.0009 | - |
|
| 471 |
+
| 2.9335 | 15650 | 0.001 | - |
|
| 472 |
+
| 2.9428 | 15700 | 0.0007 | - |
|
| 473 |
+
| 2.9522 | 15750 | 0.0012 | - |
|
| 474 |
+
| 2.9616 | 15800 | 0.0008 | - |
|
| 475 |
+
| 2.9709 | 15850 | 0.001 | - |
|
| 476 |
+
| 2.9803 | 15900 | 0.0009 | - |
|
| 477 |
+
| 2.9897 | 15950 | 0.0011 | - |
|
| 478 |
+
| 2.9991 | 16000 | 0.0005 | - |
|
| 479 |
+
|
| 480 |
+
### Framework Versions
|
| 481 |
+
- Python: 3.13.7
|
| 482 |
+
- SetFit: 1.1.3
|
| 483 |
+
- Sentence Transformers: 5.1.1
|
| 484 |
+
- Transformers: 4.57.0
|
| 485 |
+
- PyTorch: 2.8.0+cu129
|
| 486 |
+
- Datasets: 4.2.0
|
| 487 |
+
- Tokenizers: 0.22.1
|
| 488 |
+
|
| 489 |
+
## Citation
|
| 490 |
+
|
| 491 |
+
### BibTeX
|
| 492 |
+
```bibtex
|
| 493 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 494 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 495 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 496 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 497 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 498 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 499 |
+
publisher = {arXiv},
|
| 500 |
+
year = {2022},
|
| 501 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 502 |
+
}
|
| 503 |
+
```
|
| 504 |
+
|
| 505 |
+
<!--
|
| 506 |
+
## Glossary
|
| 507 |
+
|
| 508 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 509 |
+
-->
|
| 510 |
+
|
| 511 |
+
<!--
|
| 512 |
+
## Model Card Authors
|
| 513 |
+
|
| 514 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 515 |
+
-->
|
| 516 |
+
|
| 517 |
+
<!--
|
| 518 |
+
## Model Card Contact
|
| 519 |
+
|
| 520 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 521 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 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": 6,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.57.0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.1.1",
|
| 4 |
+
"transformers": "4.57.0",
|
| 5 |
+
"pytorch": "2.8.0+cu129"
|
| 6 |
+
},
|
| 7 |
+
"model_type": "SentenceTransformer",
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
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 sha256:061998cf3d0db86cdaa764ccf60c19a735a81e1efa5fa6f8f53c842c75a3c624
|
| 3 |
+
size 90864192
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6112f15eab358cae3247291e8205e02b5e42ac8855e71866da39225937491bf4
|
| 3 |
+
size 17643
|
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": 256,
|
| 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 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_length": 128,
|
| 51 |
+
"model_max_length": 256,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
+
"sep_token": "[SEP]",
|
| 58 |
+
"stride": 0,
|
| 59 |
+
"strip_accents": null,
|
| 60 |
+
"tokenize_chinese_chars": true,
|
| 61 |
+
"tokenizer_class": "BertTokenizer",
|
| 62 |
+
"truncation_side": "right",
|
| 63 |
+
"truncation_strategy": "longest_first",
|
| 64 |
+
"unk_token": "[UNK]"
|
| 65 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|