isolation-forest
commited on
Commit
•
6a64c7a
1
Parent(s):
11e2303
Add SetFit ABSA model
Browse files- 1_Pooling/config.json +10 -0
- README.md +243 -0
- config.json +27 -0
- config_sentence_transformers.json +9 -0
- config_setfit.json +10 -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": 312,
|
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 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- absa
|
6 |
+
- sentence-transformers
|
7 |
+
- text-classification
|
8 |
+
- generated_from_setfit_trainer
|
9 |
+
base_model: cointegrated/rubert-tiny2
|
10 |
+
metrics:
|
11 |
+
- accuracy
|
12 |
+
widget:
|
13 |
+
- text: Посетили вчера Твинс с подругой ,:Посетили вчера Твинс с подругой , в целом
|
14 |
+
все очень понравилось ! !
|
15 |
+
- text: ', что это кафе для тех ,:По кухне можно сказать , что это кафе для тех ,
|
16 |
+
кто любит соотношение цены и качества .'
|
17 |
+
- text: особенно шашлыки и наполеон . ( спасибо:Готовят очень вкусно , особенно шашлыки
|
18 |
+
и наполеон . ( спасибо большое поварам )
|
19 |
+
- text: 'свет , ненавязчивая музыка ( даже как:Интерьер приятный : есть гардероб ,
|
20 |
+
диваны , приглушенный свет , ненавязчивая музыка ( даже как - то раз наткнулись
|
21 |
+
там на саксофониста ) , приятная атмосфера . . .'
|
22 |
+
- text: 'отдельно : есть официанты , которые работают:По обслуживание отдельно : есть
|
23 |
+
официанты , которые работают с самого открытия - это тоже неплохой показатель
|
24 |
+
качества .'
|
25 |
+
pipeline_tag: text-classification
|
26 |
+
inference: false
|
27 |
+
---
|
28 |
+
|
29 |
+
# SetFit Polarity Model with cointegrated/rubert-tiny2
|
30 |
+
|
31 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) 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. In particular, this model is in charge of classifying aspect polarities.
|
32 |
+
|
33 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
34 |
+
|
35 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
36 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
37 |
+
|
38 |
+
This model was trained within the context of a larger system for ABSA, which looks like so:
|
39 |
+
|
40 |
+
1. Use a spaCy model to select possible aspect span candidates.
|
41 |
+
2. Use a SetFit model to filter these possible aspect span candidates.
|
42 |
+
3. **Use this SetFit model to classify the filtered aspect span candidates.**
|
43 |
+
|
44 |
+
## Model Details
|
45 |
+
|
46 |
+
### Model Description
|
47 |
+
- **Model Type:** SetFit
|
48 |
+
- **Sentence Transformer body:** [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2)
|
49 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
50 |
+
- **spaCy Model:** en_core_web_lg
|
51 |
+
- **SetFitABSA Aspect Model:** [isolation-forest/setfit-absa-aspect](https://huggingface.co/isolation-forest/setfit-absa-aspect)
|
52 |
+
- **SetFitABSA Polarity Model:** [isolation-forest/setfit-absa-polarity](https://huggingface.co/isolation-forest/setfit-absa-polarity)
|
53 |
+
- **Maximum Sequence Length:** 2048 tokens
|
54 |
+
- **Number of Classes:** 3 classes
|
55 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
56 |
+
<!-- - **Language:** Unknown -->
|
57 |
+
<!-- - **License:** Unknown -->
|
58 |
+
|
59 |
+
### Model Sources
|
60 |
+
|
61 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
62 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
63 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
64 |
+
|
65 |
+
### Model Labels
|
66 |
+
| Label | Examples |
|
67 |
+
|:---------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
68 |
+
| Positive | <ul><li>'Обслуживание хорошее нас встретил:Обслуживание хорошее нас встретил метрдотель и провёл до столика который отлично нам подашел .'</li><li>'хорошее нас встретил метрдотель и провёл до:Обслуживание хорошее нас встретил метрдотель и провёл до столика который отлично нам подашел .'</li><li>'был в уютном уголке в конце главного:Он был в уютном уголке в конце главного зала , приглушенный свет это основная часть этого ресторана там нет дневного освещения это было большим плюсом для нашего дня рожденья !'</li></ul> |
|
69 |
+
| Neutral | <ul><li>'По поводу интерьера : место спокойное:По поводу интерьера : место спокойное , шумных компаний нет ( не было , по крайней мере , в момент нашего посещения ) , очень приятная и уютная атмосфера , все в лучших традициях .'</li><li>'поводу интерьера : место спокойное , шумных:По поводу интерьера : место спокойное , шумных компаний нет ( не было , по крайней мере , в момент нашего посещения ) , очень приятная и уютная атмосфера , все в лучших традициях .'</li><li>'Интерьер не плохой ,:Интерьер не плохой , несколько залов на разный вкус и компанию .'</li></ul> |
|
70 |
+
| Negative | <ul><li>'как в работе официантов так и в:Очень много недочетов как в работе официантов так и в блюдах . 1 .'</li><li>'так и в блюдах . 1 .:Очень много недочетов как в работе официантов так и в блюдах . 1 .'</li><li>'К большому удивлению пицца ( ещё раз:К большому удивлению пицца ( ещё раз - из детского меню ! ) была на столько острая , что и взрослые не смогли её есть , не говоря уже о ребенке .'</li></ul> |
|
71 |
+
|
72 |
+
## Uses
|
73 |
+
|
74 |
+
### Direct Use for Inference
|
75 |
+
|
76 |
+
First install the SetFit library:
|
77 |
+
|
78 |
+
```bash
|
79 |
+
pip install setfit
|
80 |
+
```
|
81 |
+
|
82 |
+
Then you can load this model and run inference.
|
83 |
+
|
84 |
+
```python
|
85 |
+
from setfit import AbsaModel
|
86 |
+
|
87 |
+
# Download from the 🤗 Hub
|
88 |
+
model = AbsaModel.from_pretrained(
|
89 |
+
"isolation-forest/setfit-absa-aspect",
|
90 |
+
"isolation-forest/setfit-absa-polarity",
|
91 |
+
)
|
92 |
+
# Run inference
|
93 |
+
preds = model("The food was great, but the venue is just way too busy.")
|
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 | 5 | 27.2578 | 171 |
|
126 |
+
|
127 |
+
| Label | Training Sample Count |
|
128 |
+
|:---------|:----------------------|
|
129 |
+
| Negative | 54 |
|
130 |
+
| Neutral | 19 |
|
131 |
+
| Positive | 183 |
|
132 |
+
|
133 |
+
### Training Hyperparameters
|
134 |
+
- batch_size: (16, 2)
|
135 |
+
- num_epochs: (1, 16)
|
136 |
+
- max_steps: -1
|
137 |
+
- sampling_strategy: oversampling
|
138 |
+
- body_learning_rate: (2e-05, 1e-05)
|
139 |
+
- head_learning_rate: 0.01
|
140 |
+
- loss: CosineSimilarityLoss
|
141 |
+
- distance_metric: cosine_distance
|
142 |
+
- margin: 0.25
|
143 |
+
- end_to_end: False
|
144 |
+
- use_amp: False
|
145 |
+
- warmup_proportion: 0.1
|
146 |
+
- seed: 42
|
147 |
+
- eval_max_steps: -1
|
148 |
+
- load_best_model_at_end: False
|
149 |
+
|
150 |
+
### Training Results
|
151 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
152 |
+
|:------:|:----:|:-------------:|:---------------:|
|
153 |
+
| 0.0004 | 1 | 0.2493 | - |
|
154 |
+
| 0.0216 | 50 | 0.2343 | - |
|
155 |
+
| 0.0432 | 100 | 0.2786 | - |
|
156 |
+
| 0.0648 | 150 | 0.1976 | - |
|
157 |
+
| 0.0864 | 200 | 0.2 | - |
|
158 |
+
| 0.1080 | 250 | 0.1894 | - |
|
159 |
+
| 0.1296 | 300 | 0.081 | - |
|
160 |
+
| 0.1513 | 350 | 0.1189 | - |
|
161 |
+
| 0.1729 | 400 | 0.0279 | - |
|
162 |
+
| 0.1945 | 450 | 0.0755 | - |
|
163 |
+
| 0.2161 | 500 | 0.0436 | - |
|
164 |
+
| 0.2377 | 550 | 0.0231 | - |
|
165 |
+
| 0.2593 | 600 | 0.0088 | - |
|
166 |
+
| 0.2809 | 650 | 0.0686 | - |
|
167 |
+
| 0.3025 | 700 | 0.0138 | - |
|
168 |
+
| 0.3241 | 750 | 0.0137 | - |
|
169 |
+
| 0.3457 | 800 | 0.0087 | - |
|
170 |
+
| 0.3673 | 850 | 0.0131 | - |
|
171 |
+
| 0.3889 | 900 | 0.0245 | - |
|
172 |
+
| 0.4105 | 950 | 0.0093 | - |
|
173 |
+
| 0.4322 | 1000 | 0.0036 | - |
|
174 |
+
| 0.4538 | 1050 | 0.0149 | - |
|
175 |
+
| 0.4754 | 1100 | 0.02 | - |
|
176 |
+
| 0.4970 | 1150 | 0.0387 | - |
|
177 |
+
| 0.5186 | 1200 | 0.017 | - |
|
178 |
+
| 0.5402 | 1250 | 0.0417 | - |
|
179 |
+
| 0.5618 | 1300 | 0.0041 | - |
|
180 |
+
| 0.5834 | 1350 | 0.0041 | - |
|
181 |
+
| 0.6050 | 1400 | 0.0282 | - |
|
182 |
+
| 0.6266 | 1450 | 0.0102 | - |
|
183 |
+
| 0.6482 | 1500 | 0.0037 | - |
|
184 |
+
| 0.6698 | 1550 | 0.0058 | - |
|
185 |
+
| 0.6914 | 1600 | 0.0078 | - |
|
186 |
+
| 0.7131 | 1650 | 0.0272 | - |
|
187 |
+
| 0.7347 | 1700 | 0.0224 | - |
|
188 |
+
| 0.7563 | 1750 | 0.0057 | - |
|
189 |
+
| 0.7779 | 1800 | 0.0026 | - |
|
190 |
+
| 0.7995 | 1850 | 0.0088 | - |
|
191 |
+
| 0.8211 | 1900 | 0.0044 | - |
|
192 |
+
| 0.8427 | 1950 | 0.005 | - |
|
193 |
+
| 0.8643 | 2000 | 0.0026 | - |
|
194 |
+
| 0.8859 | 2050 | 0.0072 | - |
|
195 |
+
| 0.9075 | 2100 | 0.0033 | - |
|
196 |
+
| 0.9291 | 2150 | 0.0047 | - |
|
197 |
+
| 0.9507 | 2200 | 0.0048 | - |
|
198 |
+
| 0.9723 | 2250 | 0.0042 | - |
|
199 |
+
| 0.9939 | 2300 | 0.0043 | - |
|
200 |
+
|
201 |
+
### Framework Versions
|
202 |
+
- Python: 3.10.13
|
203 |
+
- SetFit: 1.0.3
|
204 |
+
- Sentence Transformers: 2.6.1
|
205 |
+
- spaCy: 3.7.2
|
206 |
+
- Transformers: 4.39.3
|
207 |
+
- PyTorch: 2.1.2
|
208 |
+
- Datasets: 2.18.0
|
209 |
+
- Tokenizers: 0.15.2
|
210 |
+
|
211 |
+
## Citation
|
212 |
+
|
213 |
+
### BibTeX
|
214 |
+
```bibtex
|
215 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
216 |
+
doi = {10.48550/ARXIV.2209.11055},
|
217 |
+
url = {https://arxiv.org/abs/2209.11055},
|
218 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
219 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
220 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
221 |
+
publisher = {arXiv},
|
222 |
+
year = {2022},
|
223 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
224 |
+
}
|
225 |
+
```
|
226 |
+
|
227 |
+
<!--
|
228 |
+
## Glossary
|
229 |
+
|
230 |
+
*Clearly define terms in order to be accessible across audiences.*
|
231 |
+
-->
|
232 |
+
|
233 |
+
<!--
|
234 |
+
## Model Card Authors
|
235 |
+
|
236 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
237 |
+
-->
|
238 |
+
|
239 |
+
<!--
|
240 |
+
## Model Card Contact
|
241 |
+
|
242 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
243 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 600,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 3,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.39.3",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 83828
|
27 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.6.1",
|
4 |
+
"transformers": "4.39.3",
|
5 |
+
"pytorch": "2.1.2"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"spacy_model": "en_core_web_lg",
|
3 |
+
"span_context": 3,
|
4 |
+
"labels": [
|
5 |
+
"Negative",
|
6 |
+
"Neutral",
|
7 |
+
"Positive"
|
8 |
+
],
|
9 |
+
"normalize_embeddings": false
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90b6e9531d682448e17bce1556afe812d825b50690f20c992340e8d76cb07adc
|
3 |
+
size 116781184
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fcaa9b95e91a59691a442788cdb7e2fb9b979dad928fe94df42129686ad7c33
|
3 |
+
size 8431
|
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": 2048,
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 2048,
|
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
|
|