adriansanz
commited on
Commit
•
bce94f9
1
Parent(s):
2d4e6ad
Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +230 -0
- config.json +40 -0
- config_sentence_transformers.json +9 -0
- config_setfit.json +4 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- vocab.json +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,230 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 'Neteja a deshores : Avui a les 7:30 del matí i s''ha presentat un senyor
|
12 |
+
amb una furgoneta de LLEIDA MÉS NETA al carrer dels Agustins i amb una mànega
|
13 |
+
a pressió i el seu compressor s''ha disposat a netejar el mobiliari urbà fins
|
14 |
+
a les 07:45. Cada cop que apretava la mànega es disparava el compresor fent així
|
15 |
+
molt soroll i finalment despertant a la canalla que ja tenen els dies comçlicats
|
16 |
+
com per a que se''ls allarguin més encara A les 7:30 està prohibit fer soroll.
|
17 |
+
Tinc varies fotos que ho demostren.'
|
18 |
+
- text: 'Barana del canal : A l’alçada del canal del c/. Enginyer Antoni Llobet esta
|
19 |
+
instal.lada una barana que presenta un espai per la zona inferior que pot generar
|
20 |
+
un accident,doncs es una zona molt transitada per nens i si cauen per allí perfectament
|
21 |
+
es poden colar per sota i caure al canal. Sol.licito que hi fiquin algun tipo
|
22 |
+
de protecció.'
|
23 |
+
- text: 'Escola de música d''adults : Hola. Voldria suggerir que féssiu algun descompte
|
24 |
+
a l''Escola de música d''adults per les persones amb discapacitat. Gràcies.'
|
25 |
+
- text: 'Expedient DU13-380 Negociat de Disciplina Ue : Benvolguts Srs, Avui ens hem
|
26 |
+
personat a l''edifici Pal.las per contactar amb el Negociat de Disciplina Urbanística
|
27 |
+
i donar una resposta personal al requeriment. Estem en contacte amb un arquitecte
|
28 |
+
qui presentarà en breu els documents requerits. La persona d''Urbanisme que ens
|
29 |
+
ha atès aquest matí ens ha suggerit que presentéssim telemàticament l''escrit
|
30 |
+
que volíem avui mateix aportar al Negociat, i que adjuntem. Rebin una salutació,
|
31 |
+
Elisa Rosanes i Joan Valls'
|
32 |
+
- text: 'Bonificació escola bressol : Bones, vaig fer la tramitació per família monoparental
|
33 |
+
per l''escola bressol la mitjana pero no s''he m''ha aplicat, ja que posa que
|
34 |
+
la cuantitar a pagar son 90 euros mensuals. He tornat a fer la solicitud per si
|
35 |
+
hi hagut algun problema. També voldria saber si ja esta aplicat el servei de menjador.
|
36 |
+
Gràcies.'
|
37 |
+
pipeline_tag: text-classification
|
38 |
+
inference: true
|
39 |
+
base_model: ibaucells/RoBERTa-ca-CaWikiTC
|
40 |
+
---
|
41 |
+
|
42 |
+
# SetFit with ibaucells/RoBERTa-ca-CaWikiTC
|
43 |
+
|
44 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [ibaucells/RoBERTa-ca-CaWikiTC](https://huggingface.co/ibaucells/RoBERTa-ca-CaWikiTC) 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.
|
45 |
+
|
46 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
47 |
+
|
48 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
49 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
50 |
+
|
51 |
+
## Model Details
|
52 |
+
|
53 |
+
### Model Description
|
54 |
+
- **Model Type:** SetFit
|
55 |
+
- **Sentence Transformer body:** [ibaucells/RoBERTa-ca-CaWikiTC](https://huggingface.co/ibaucells/RoBERTa-ca-CaWikiTC)
|
56 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
57 |
+
- **Maximum Sequence Length:** 512 tokens
|
58 |
+
- **Number of Classes:** 17 classes
|
59 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
60 |
+
<!-- - **Language:** Unknown -->
|
61 |
+
<!-- - **License:** Unknown -->
|
62 |
+
|
63 |
+
### Model Sources
|
64 |
+
|
65 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
66 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
67 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
68 |
+
|
69 |
+
### Model Labels
|
70 |
+
| Label | Examples |
|
71 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
72 |
+
| 0 | <ul><li>'Aquest article tracta sobre Aigües'</li><li>'Aquest article tracta sobre Aigües'</li><li>'Aquest article tracta sobre Aigües'</li></ul> |
|
73 |
+
| 1 | <ul><li>'Aquest article tracta sobre Comerç i mercats'</li><li>'Aquest article tracta sobre Comerç i mercats'</li><li>'Aquest article tracta sobre Comerç i mercats'</li></ul> |
|
74 |
+
| 2 | <ul><li>'Aquest article tracta sobre Cultura'</li><li>'Aquest article tracta sobre Cultura'</li><li>'Aquest article tracta sobre Cultura'</li></ul> |
|
75 |
+
| 3 | <ul><li>'Aquest article tracta sobre Economia'</li><li>'Aquest article tracta sobre Economia'</li><li>'Aquest article tracta sobre Economia'</li></ul> |
|
76 |
+
| 4 | <ul><li>'Aquest article tracta sobre Educació'</li><li>'Aquest article tracta sobre Educació'</li><li>'Aquest article tracta sobre Educació'</li></ul> |
|
77 |
+
| 5 | <ul><li>'Aquest article tracta sobre Enllumenat'</li><li>'Aquest article tracta sobre Enllumenat'</li><li>'Aquest article tracta sobre Enllumenat'</li></ul> |
|
78 |
+
| 6 | <ul><li>'Aquest article tracta sobre Esports'</li><li>'Aquest article tracta sobre Esports'</li><li>'Aquest article tracta sobre Esports'</li></ul> |
|
79 |
+
| 7 | <ul><li>'Aquest article tracta sobre Habitatge'</li><li>'Aquest article tracta sobre Habitatge'</li><li>'Aquest article tracta sobre Habitatge'</li></ul> |
|
80 |
+
| 8 | <ul><li>'Aquest article tracta sobre Horta'</li><li>'Aquest article tracta sobre Horta'</li><li>'Aquest article tracta sobre Horta'</li></ul> |
|
81 |
+
| 9 | <ul><li>'Aquest article tracta sobre Medi ambient'</li><li>'Aquest article tracta sobre Medi ambient'</li><li>'Aquest article tracta sobre Medi ambient'</li></ul> |
|
82 |
+
| 10 | <ul><li>'Aquest article tracta sobre Mobilitat'</li><li>'Aquest article tracta sobre Mobilitat'</li><li>'Aquest article tracta sobre Mobilitat'</li></ul> |
|
83 |
+
| 11 | <ul><li>'Aquest article tracta sobre Neteja'</li><li>'Aquest article tracta sobre Neteja'</li><li>'Aquest article tracta sobre Neteja'</li></ul> |
|
84 |
+
| 12 | <ul><li>'Aquest article tracta sobre Salut'</li><li>'Aquest article tracta sobre Salut'</li><li>'Aquest article tracta sobre Salut'</li></ul> |
|
85 |
+
| 13 | <ul><li>'Aquest article tracta sobre Seguretat'</li><li>'Aquest article tracta sobre Seguretat'</li><li>'Aquest article tracta sobre Seguretat'</li></ul> |
|
86 |
+
| 14 | <ul><li>'Aquest article tracta sobre Serveis socials'</li><li>'Aquest article tracta sobre Serveis socials'</li><li>'Aquest article tracta sobre Serveis socials'</li></ul> |
|
87 |
+
| 15 | <ul><li>'Aquest article tracta sobre Tramitacions'</li><li>'Aquest article tracta sobre Tramitacions'</li><li>'Aquest article tracta sobre Tramitacions'</li></ul> |
|
88 |
+
| 16 | <ul><li>'Aquest article tracta sobre Urbanisme'</li><li>'Aquest article tracta sobre Urbanisme'</li><li>'Aquest article tracta sobre Urbanisme'</li></ul> |
|
89 |
+
|
90 |
+
## Uses
|
91 |
+
|
92 |
+
### Direct Use for Inference
|
93 |
+
|
94 |
+
First install the SetFit library:
|
95 |
+
|
96 |
+
```bash
|
97 |
+
pip install setfit
|
98 |
+
```
|
99 |
+
|
100 |
+
Then you can load this model and run inference.
|
101 |
+
|
102 |
+
```python
|
103 |
+
from setfit import SetFitModel
|
104 |
+
|
105 |
+
# Download from the 🤗 Hub
|
106 |
+
model = SetFitModel.from_pretrained("adriansanz/test8")
|
107 |
+
# Run inference
|
108 |
+
preds = model("Escola de música d'adults : Hola. Voldria suggerir que féssiu algun descompte a l'Escola de música d'adults per les persones amb discapacitat. Gràcies.")
|
109 |
+
```
|
110 |
+
|
111 |
+
<!--
|
112 |
+
### Downstream Use
|
113 |
+
|
114 |
+
*List how someone could finetune this model on their own dataset.*
|
115 |
+
-->
|
116 |
+
|
117 |
+
<!--
|
118 |
+
### Out-of-Scope Use
|
119 |
+
|
120 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
121 |
+
-->
|
122 |
+
|
123 |
+
<!--
|
124 |
+
## Bias, Risks and Limitations
|
125 |
+
|
126 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
127 |
+
-->
|
128 |
+
|
129 |
+
<!--
|
130 |
+
### Recommendations
|
131 |
+
|
132 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
133 |
+
-->
|
134 |
+
|
135 |
+
## Training Details
|
136 |
+
|
137 |
+
### Training Set Metrics
|
138 |
+
| Training set | Min | Median | Max |
|
139 |
+
|:-------------|:----|:-------|:----|
|
140 |
+
| Word count | 5 | 5.2353 | 7 |
|
141 |
+
|
142 |
+
| Label | Training Sample Count |
|
143 |
+
|:------|:----------------------|
|
144 |
+
| 0 | 8 |
|
145 |
+
| 1 | 8 |
|
146 |
+
| 2 | 8 |
|
147 |
+
| 3 | 8 |
|
148 |
+
| 4 | 8 |
|
149 |
+
| 5 | 8 |
|
150 |
+
| 6 | 8 |
|
151 |
+
| 7 | 8 |
|
152 |
+
| 8 | 8 |
|
153 |
+
| 9 | 8 |
|
154 |
+
| 10 | 8 |
|
155 |
+
| 11 | 8 |
|
156 |
+
| 12 | 8 |
|
157 |
+
| 13 | 8 |
|
158 |
+
| 14 | 8 |
|
159 |
+
| 15 | 8 |
|
160 |
+
| 16 | 8 |
|
161 |
+
|
162 |
+
### Training Hyperparameters
|
163 |
+
- batch_size: (64, 64)
|
164 |
+
- num_epochs: (60, 60)
|
165 |
+
- max_steps: -1
|
166 |
+
- sampling_strategy: oversampling
|
167 |
+
- body_learning_rate: (2e-05, 1e-05)
|
168 |
+
- head_learning_rate: 0.01
|
169 |
+
- loss: CosineSimilarityLoss
|
170 |
+
- distance_metric: cosine_distance
|
171 |
+
- margin: 0.25
|
172 |
+
- end_to_end: False
|
173 |
+
- use_amp: False
|
174 |
+
- warmup_proportion: 0.1
|
175 |
+
- seed: 42
|
176 |
+
- eval_max_steps: -1
|
177 |
+
- load_best_model_at_end: True
|
178 |
+
|
179 |
+
### Training Results
|
180 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
181 |
+
|:------:|:----:|:-------------:|:---------------:|
|
182 |
+
| 0.0037 | 1 | 0.4079 | - |
|
183 |
+
| 0.1838 | 50 | 0.3625 | - |
|
184 |
+
| 0.3676 | 100 | 0.3197 | - |
|
185 |
+
| 0.5515 | 150 | 0.22 | - |
|
186 |
+
| 0.7353 | 200 | 0.2259 | - |
|
187 |
+
| 0.9191 | 250 | 0.1748 | - |
|
188 |
+
|
189 |
+
### Framework Versions
|
190 |
+
- Python: 3.10.12
|
191 |
+
- SetFit: 1.0.3
|
192 |
+
- Sentence Transformers: 2.6.1
|
193 |
+
- Transformers: 4.38.2
|
194 |
+
- PyTorch: 2.2.1+cu121
|
195 |
+
- Datasets: 2.18.0
|
196 |
+
- Tokenizers: 0.15.2
|
197 |
+
|
198 |
+
## Citation
|
199 |
+
|
200 |
+
### BibTeX
|
201 |
+
```bibtex
|
202 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
203 |
+
doi = {10.48550/ARXIV.2209.11055},
|
204 |
+
url = {https://arxiv.org/abs/2209.11055},
|
205 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
206 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
207 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
208 |
+
publisher = {arXiv},
|
209 |
+
year = {2022},
|
210 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
211 |
+
}
|
212 |
+
```
|
213 |
+
|
214 |
+
<!--
|
215 |
+
## Glossary
|
216 |
+
|
217 |
+
*Clearly define terms in order to be accessible across audiences.*
|
218 |
+
-->
|
219 |
+
|
220 |
+
<!--
|
221 |
+
## Model Card Authors
|
222 |
+
|
223 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
224 |
+
-->
|
225 |
+
|
226 |
+
<!--
|
227 |
+
## Model Card Contact
|
228 |
+
|
229 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
230 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ibaucells/RoBERTa-ca-CaWikiTC",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"finetuning_task": "mnli",
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "entailment",
|
17 |
+
"1": "neutral",
|
18 |
+
"2": "contradiction"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"contradiction": 2,
|
24 |
+
"entailment": 0,
|
25 |
+
"neutral": 1
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-05,
|
28 |
+
"max_position_embeddings": 514,
|
29 |
+
"model_type": "roberta",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.38.2",
|
37 |
+
"type_vocab_size": 1,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50262
|
40 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.6.1",
|
4 |
+
"transformers": "4.38.2",
|
5 |
+
"pytorch": "2.2.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": null,
|
3 |
+
"normalize_embeddings": false
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f11b8907b5d6616602c988a2c81e9564fc04d5796808a2308545fa5422d5a659
|
3 |
+
size 498595688
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95a2349eb3f96eb70d9185b2f02af4ffabe28566b0bbeda0ad56312e9e6879cb
|
3 |
+
size 324
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
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 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
+
"max_length": 512,
|
53 |
+
"model_max_length": 512,
|
54 |
+
"pad_to_multiple_of": null,
|
55 |
+
"pad_token": "<pad>",
|
56 |
+
"pad_token_type_id": 0,
|
57 |
+
"padding_side": "right",
|
58 |
+
"sep_token": "</s>",
|
59 |
+
"stride": 0,
|
60 |
+
"tokenizer_class": "RobertaTokenizer",
|
61 |
+
"trim_offsets": true,
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
+
"unk_token": "<unk>"
|
65 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|