super-cinnamon
commited on
Commit
•
b2bafa7
1
Parent(s):
3910f8a
Push model using huggingface_hub.
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +7 -0
- README.md +269 -0
- config.json +26 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +7 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
widget:
|
11 |
+
- text: Quels sont les recours possibles en cas de conflit entre un employeur et un
|
12 |
+
employé ?
|
13 |
+
- text: Comment déclarer mes impôts et taxes ?
|
14 |
+
- text: Quelles sont les règles de tenue de la comptabilité ?
|
15 |
+
- text: Quels sont les frais associés à cette procédure ?
|
16 |
+
- text: Quelles sont les procédures de recours possibles contre une décision administrative
|
17 |
+
?
|
18 |
+
pipeline_tag: text-classification
|
19 |
+
inference: true
|
20 |
+
base_model: intfloat/multilingual-e5-small
|
21 |
+
model-index:
|
22 |
+
- name: SetFit with intfloat/multilingual-e5-small
|
23 |
+
results:
|
24 |
+
- task:
|
25 |
+
type: text-classification
|
26 |
+
name: Text Classification
|
27 |
+
dataset:
|
28 |
+
name: Unknown
|
29 |
+
type: unknown
|
30 |
+
split: test
|
31 |
+
metrics:
|
32 |
+
- type: accuracy
|
33 |
+
value: 0.9473684210526315
|
34 |
+
name: Accuracy
|
35 |
+
---
|
36 |
+
|
37 |
+
# SetFit with intfloat/multilingual-e5-small
|
38 |
+
|
39 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) 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.
|
40 |
+
|
41 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
42 |
+
|
43 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
44 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
45 |
+
|
46 |
+
## Model Details
|
47 |
+
|
48 |
+
### Model Description
|
49 |
+
- **Model Type:** SetFit
|
50 |
+
- **Sentence Transformer body:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)
|
51 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
52 |
+
- **Maximum Sequence Length:** 512 tokens
|
53 |
+
- **Number of Classes:** 2 classes
|
54 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
55 |
+
<!-- - **Language:** Unknown -->
|
56 |
+
<!-- - **License:** Unknown -->
|
57 |
+
|
58 |
+
### Model Sources
|
59 |
+
|
60 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
61 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
62 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
63 |
+
|
64 |
+
### Model Labels
|
65 |
+
| Label | Examples |
|
66 |
+
|:------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
67 |
+
| follow_up | <ul><li>'Quels sont les régimes matrimoniaux possibles ?'</li><li>'Quelles sont les conséquences économiques ou sociales de cette loi ?'</li><li>"Est-ce que cette loi s'applique à mon cas particulier ?"</li></ul> |
|
68 |
+
| independent | <ul><li>'Quelles sont les règles en matière de temps de travail et de congés ?'</li><li>"Quels sont les types de structures d'entreprise autorisés en Algérie ?"</li><li>'Quels sont les droits et obligations des travailleurs en Algérie ?'</li></ul> |
|
69 |
+
|
70 |
+
## Evaluation
|
71 |
+
|
72 |
+
### Metrics
|
73 |
+
| Label | Accuracy |
|
74 |
+
|:--------|:---------|
|
75 |
+
| **all** | 0.9474 |
|
76 |
+
|
77 |
+
## Uses
|
78 |
+
|
79 |
+
### Direct Use for Inference
|
80 |
+
|
81 |
+
First install the SetFit library:
|
82 |
+
|
83 |
+
```bash
|
84 |
+
pip install setfit
|
85 |
+
```
|
86 |
+
|
87 |
+
Then you can load this model and run inference.
|
88 |
+
|
89 |
+
```python
|
90 |
+
from setfit import SetFitModel
|
91 |
+
|
92 |
+
# Download from the 🤗 Hub
|
93 |
+
model = SetFitModel.from_pretrained("super-cinnamon/fewshot-followup-multi-e5")
|
94 |
+
# Run inference
|
95 |
+
preds = model("Comment déclarer mes impôts et taxes ?")
|
96 |
+
```
|
97 |
+
|
98 |
+
<!--
|
99 |
+
### Downstream Use
|
100 |
+
|
101 |
+
*List how someone could finetune this model on their own dataset.*
|
102 |
+
-->
|
103 |
+
|
104 |
+
<!--
|
105 |
+
### Out-of-Scope Use
|
106 |
+
|
107 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
108 |
+
-->
|
109 |
+
|
110 |
+
<!--
|
111 |
+
## Bias, Risks and Limitations
|
112 |
+
|
113 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
114 |
+
-->
|
115 |
+
|
116 |
+
<!--
|
117 |
+
### Recommendations
|
118 |
+
|
119 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
120 |
+
-->
|
121 |
+
|
122 |
+
## Training Details
|
123 |
+
|
124 |
+
### Training Set Metrics
|
125 |
+
| Training set | Min | Median | Max |
|
126 |
+
|:-------------|:----|:-------|:----|
|
127 |
+
| Word count | 2 | 9.76 | 16 |
|
128 |
+
|
129 |
+
| Label | Training Sample Count |
|
130 |
+
|:------------|:----------------------|
|
131 |
+
| independent | 39 |
|
132 |
+
| follow_up | 36 |
|
133 |
+
|
134 |
+
### Training Hyperparameters
|
135 |
+
- batch_size: (8, 8)
|
136 |
+
- num_epochs: (10, 10)
|
137 |
+
- max_steps: -1
|
138 |
+
- sampling_strategy: oversampling
|
139 |
+
- body_learning_rate: (2e-05, 1e-05)
|
140 |
+
- head_learning_rate: 0.01
|
141 |
+
- loss: CosineSimilarityLoss
|
142 |
+
- distance_metric: cosine_distance
|
143 |
+
- margin: 0.25
|
144 |
+
- end_to_end: False
|
145 |
+
- use_amp: False
|
146 |
+
- warmup_proportion: 0.1
|
147 |
+
- seed: 42
|
148 |
+
- eval_max_steps: -1
|
149 |
+
- load_best_model_at_end: False
|
150 |
+
|
151 |
+
### Training Results
|
152 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
153 |
+
|:------:|:----:|:-------------:|:---------------:|
|
154 |
+
| 0.0028 | 1 | 0.3779 | - |
|
155 |
+
| 0.1381 | 50 | 0.3395 | - |
|
156 |
+
| 0.2762 | 100 | 0.1385 | - |
|
157 |
+
| 0.4144 | 150 | 0.1179 | - |
|
158 |
+
| 0.5525 | 200 | 0.0172 | - |
|
159 |
+
| 0.6906 | 250 | 0.0006 | - |
|
160 |
+
| 0.8287 | 300 | 0.0014 | - |
|
161 |
+
| 0.9669 | 350 | 0.0004 | - |
|
162 |
+
| 1.1050 | 400 | 0.0002 | - |
|
163 |
+
| 1.2431 | 450 | 0.0002 | - |
|
164 |
+
| 1.3812 | 500 | 0.0002 | - |
|
165 |
+
| 1.5193 | 550 | 0.0005 | - |
|
166 |
+
| 1.6575 | 600 | 0.0001 | - |
|
167 |
+
| 1.7956 | 650 | 0.0001 | - |
|
168 |
+
| 1.9337 | 700 | 0.0001 | - |
|
169 |
+
| 2.0718 | 750 | 0.0002 | - |
|
170 |
+
| 2.2099 | 800 | 0.0001 | - |
|
171 |
+
| 2.3481 | 850 | 0.0002 | - |
|
172 |
+
| 2.4862 | 900 | 0.0003 | - |
|
173 |
+
| 2.6243 | 950 | 0.0001 | - |
|
174 |
+
| 2.7624 | 1000 | 0.0001 | - |
|
175 |
+
| 2.9006 | 1050 | 0.0001 | - |
|
176 |
+
| 3.0387 | 1100 | 0.0 | - |
|
177 |
+
| 3.1768 | 1150 | 0.0001 | - |
|
178 |
+
| 3.3149 | 1200 | 0.0001 | - |
|
179 |
+
| 3.4530 | 1250 | 0.0001 | - |
|
180 |
+
| 3.5912 | 1300 | 0.0001 | - |
|
181 |
+
| 3.7293 | 1350 | 0.0 | - |
|
182 |
+
| 3.8674 | 1400 | 0.0001 | - |
|
183 |
+
| 4.0055 | 1450 | 0.0001 | - |
|
184 |
+
| 4.1436 | 1500 | 0.0001 | - |
|
185 |
+
| 4.2818 | 1550 | 0.0002 | - |
|
186 |
+
| 4.4199 | 1600 | 0.0001 | - |
|
187 |
+
| 4.5580 | 1650 | 0.0001 | - |
|
188 |
+
| 4.6961 | 1700 | 0.0002 | - |
|
189 |
+
| 4.8343 | 1750 | 0.0 | - |
|
190 |
+
| 4.9724 | 1800 | 0.0001 | - |
|
191 |
+
| 5.1105 | 1850 | 0.0 | - |
|
192 |
+
| 5.2486 | 1900 | 0.0001 | - |
|
193 |
+
| 5.3867 | 1950 | 0.0 | - |
|
194 |
+
| 5.5249 | 2000 | 0.0 | - |
|
195 |
+
| 5.6630 | 2050 | 0.0001 | - |
|
196 |
+
| 5.8011 | 2100 | 0.0 | - |
|
197 |
+
| 5.9392 | 2150 | 0.0 | - |
|
198 |
+
| 6.0773 | 2200 | 0.0001 | - |
|
199 |
+
| 6.2155 | 2250 | 0.0001 | - |
|
200 |
+
| 6.3536 | 2300 | 0.0001 | - |
|
201 |
+
| 6.4917 | 2350 | 0.0 | - |
|
202 |
+
| 6.6298 | 2400 | 0.0 | - |
|
203 |
+
| 6.7680 | 2450 | 0.0 | - |
|
204 |
+
| 6.9061 | 2500 | 0.0 | - |
|
205 |
+
| 7.0442 | 2550 | 0.0 | - |
|
206 |
+
| 7.1823 | 2600 | 0.0001 | - |
|
207 |
+
| 7.3204 | 2650 | 0.0 | - |
|
208 |
+
| 7.4586 | 2700 | 0.0 | - |
|
209 |
+
| 7.5967 | 2750 | 0.0001 | - |
|
210 |
+
| 7.7348 | 2800 | 0.0 | - |
|
211 |
+
| 7.8729 | 2850 | 0.0001 | - |
|
212 |
+
| 8.0110 | 2900 | 0.0 | - |
|
213 |
+
| 8.1492 | 2950 | 0.0 | - |
|
214 |
+
| 8.2873 | 3000 | 0.0 | - |
|
215 |
+
| 8.4254 | 3050 | 0.0 | - |
|
216 |
+
| 8.5635 | 3100 | 0.0001 | - |
|
217 |
+
| 8.7017 | 3150 | 0.0 | - |
|
218 |
+
| 8.8398 | 3200 | 0.0001 | - |
|
219 |
+
| 8.9779 | 3250 | 0.0 | - |
|
220 |
+
| 9.1160 | 3300 | 0.0 | - |
|
221 |
+
| 9.2541 | 3350 | 0.0 | - |
|
222 |
+
| 9.3923 | 3400 | 0.0 | - |
|
223 |
+
| 9.5304 | 3450 | 0.0 | - |
|
224 |
+
| 9.6685 | 3500 | 0.0 | - |
|
225 |
+
| 9.8066 | 3550 | 0.0 | - |
|
226 |
+
| 9.9448 | 3600 | 0.0 | - |
|
227 |
+
|
228 |
+
### Framework Versions
|
229 |
+
- Python: 3.10.12
|
230 |
+
- SetFit: 1.0.1
|
231 |
+
- Sentence Transformers: 2.2.2
|
232 |
+
- Transformers: 4.35.2
|
233 |
+
- PyTorch: 2.1.0+cu118
|
234 |
+
- Datasets: 2.15.0
|
235 |
+
- Tokenizers: 0.15.0
|
236 |
+
|
237 |
+
## Citation
|
238 |
+
|
239 |
+
### BibTeX
|
240 |
+
```bibtex
|
241 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
242 |
+
doi = {10.48550/ARXIV.2209.11055},
|
243 |
+
url = {https://arxiv.org/abs/2209.11055},
|
244 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
245 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
246 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
247 |
+
publisher = {arXiv},
|
248 |
+
year = {2022},
|
249 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
250 |
+
}
|
251 |
+
```
|
252 |
+
|
253 |
+
<!--
|
254 |
+
## Glossary
|
255 |
+
|
256 |
+
*Clearly define terms in order to be accessible across audiences.*
|
257 |
+
-->
|
258 |
+
|
259 |
+
<!--
|
260 |
+
## Model Card Authors
|
261 |
+
|
262 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
263 |
+
-->
|
264 |
+
|
265 |
+
<!--
|
266 |
+
## Model Card Contact
|
267 |
+
|
268 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
269 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-small/",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 384,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1536,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.35.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.35.2",
|
5 |
+
"pytorch": "2.1.0+cu118"
|
6 |
+
}
|
7 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": [
|
3 |
+
"independent",
|
4 |
+
"follow_up"
|
5 |
+
],
|
6 |
+
"normalize_embeddings": false
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5edb798d3bd404c37447047f5afda2cdad776e104cc8272895926d747735ca75
|
3 |
+
size 470637416
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21c3b1bfac2f76b5384939f137e1092bd4f06771646265e3952af3c4161c44a0
|
3 |
+
size 3919
|
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": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39feb9863a378165ab9c5c689047203d789422966c0c58721c5309fd039a8edc
|
3 |
+
size 17083074
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|