Add SetFit model
Browse files- 1_Pooling/config.json +7 -0
- README.md +219 -0
- config.json +24 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +4 -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 +59 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 'The Alavas worked themselves to the bone in the last period , and English
|
12 |
+
and San Emeterio ( 65-75 ) had already made it clear that they were not going
|
13 |
+
to let anyone take away what they had earned during the first thirty minutes . '
|
14 |
+
- text: 'To break the uncomfortable silence , Haney began to talk . '
|
15 |
+
- text: 'For the treatment of non-small cell lung cancer , the effects of Alimta were
|
16 |
+
compared with those of docetaxel ( another anticancer medicine ) in one study
|
17 |
+
involving 571 patients with locally advanced or metastatic disease who had received
|
18 |
+
chemotherapy in the past . '
|
19 |
+
- text: 'As we all know , a few minutes before the end of the game ( that their team
|
20 |
+
had already won ) , both players deliberately wasted time which made the referee
|
21 |
+
show the second yellow card to both of them . '
|
22 |
+
- text: 'In contrast , patients whose cancer was affecting squamous cells had shorter
|
23 |
+
survival times if they received Alimta . '
|
24 |
+
pipeline_tag: text-classification
|
25 |
+
inference: true
|
26 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
27 |
+
model-index:
|
28 |
+
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
29 |
+
results:
|
30 |
+
- task:
|
31 |
+
type: text-classification
|
32 |
+
name: Text Classification
|
33 |
+
dataset:
|
34 |
+
name: Unknown
|
35 |
+
type: unknown
|
36 |
+
split: test
|
37 |
+
metrics:
|
38 |
+
- type: accuracy
|
39 |
+
value: 0.17086092715231788
|
40 |
+
name: Accuracy
|
41 |
+
---
|
42 |
+
|
43 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
44 |
+
|
45 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification.
|
46 |
+
|
47 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
48 |
+
|
49 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
50 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
51 |
+
|
52 |
+
## Model Details
|
53 |
+
|
54 |
+
### Model Description
|
55 |
+
- **Model Type:** SetFit
|
56 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
57 |
+
- **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance
|
58 |
+
- **Maximum Sequence Length:** 512 tokens
|
59 |
+
- **Number of Classes:** 7 classes
|
60 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
61 |
+
<!-- - **Language:** Unknown -->
|
62 |
+
<!-- - **License:** Unknown -->
|
63 |
+
|
64 |
+
### Model Sources
|
65 |
+
|
66 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
67 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
68 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
69 |
+
|
70 |
+
### Model Labels
|
71 |
+
| Label | Examples |
|
72 |
+
|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
73 |
+
| 3 | <ul><li>'Saves the log with all results into an HTML file to be able to print or publish . '</li><li>'Alimta is used together with cisplatin ( another anticancer medicine ) when the cancer is unresectable ( cannot be removed by surgery alone ) and malignant ( has spread , or is likely to spread easily , to other parts of the body ) , in patients who have not received chemotherapy ( medicines for cancer ) before advanced or metastatic non-small cell lung cancer that is not affecting the squamous cells . '</li><li>"It was the most exercise we 'd had all morning and it was followed by our driving immediately to the nearest watering hole . "</li></ul> |
|
74 |
+
| 6 | <ul><li>'3 -RRB- Republican congressional representatives , because of their belief in a minimalist state , are less willing to engage in local benefit-seeking than are Democratic members of Congress . '</li><li>'Here , the experience of New York City is decisive . '</li><li>'The idea would be to administer to patients the growth-controlling proteins made by healthy versions of the damaged genes . '</li></ul> |
|
75 |
+
| 2 | <ul><li>'-- Students should move up the educational ladder as their academic potential allows . '</li><li>'The next day , Sunday , the hangover reminded Haney where he had been the night before . '</li><li>'It explains how the Committee for Medicinal Products for Veterinary Use ( CVMP ) assessed the studies performed , to reach their recommendations on how to use the medicine . '</li></ul> |
|
76 |
+
| 0 | <ul><li>'A minor contrast to Costa Rica , comparing the 22 players called by both countries for the friendly game today , at 3:05 pm at the National Stadium in San Jose . '</li><li>'Never in my life have I been so frightened . '</li><li>'Prior to 1932 , the pattern was nearly the opposite . '</li></ul> |
|
77 |
+
| 5 | <ul><li>'2 -RRB- Congressional representatives have two basic responsibilities while voting in office -- dealing with national issues -LRB- programmatic actions such as casting roll call votes on legislation that imposes costs and/or confers benefits on the population at large -RRB- and attending to local issues -LRB- constituency service and pork barrel -RRB- . '</li><li>'The scientists say that since breast cancer often strikes multiple members of certain families , the gene , when inherited in a damaged form , may predispose women to the cancer . '</li><li>"On the Right , the tone was set by Jacques Chirac , who declared in 1976 that `` 900,000 unemployed would not become a problem in a country with 2 million of foreign workers , '' and on the Left by Michel Rocard explaining in 1990 that France `` can not accommodate all the world 's misery . '' "</li></ul> |
|
78 |
+
| 4 | <ul><li>'Researchers say the inactivation of tumor-suppressor genes , alone or in combination , appears crucial to the development of such scourges as cancer of the brain , the skin , kidney , prostate , and cervix . '</li><li>'One writer , signing his letter as `` Red-blooded , balanced male , `` remarked on the `` frequency of women fainting in peals , `` and suggested that they `` settle back into their traditional role of making tea at meetings . `` '</li><li>'`` To ring for even one service at this tower , we have to scrape , `` says Mr. Hammond , a retired water-authority worker . `` '</li></ul> |
|
79 |
+
| 1 | <ul><li>"kalgebra 's console is useful as a calculator . "</li><li>'Mr. Neuberger realized that , although of Italian ancestry , Mr. Mariotta still could qualify as a minority person since he was born in Puerto Rico . '</li><li>"Biggest trouble was scared family who could n't get a phone line through , and spent a really horrible hour not knowing . "</li></ul> |
|
80 |
+
|
81 |
+
## Evaluation
|
82 |
+
|
83 |
+
### Metrics
|
84 |
+
| Label | Accuracy |
|
85 |
+
|:--------|:---------|
|
86 |
+
| **all** | 0.1709 |
|
87 |
+
|
88 |
+
## Uses
|
89 |
+
|
90 |
+
### Direct Use for Inference
|
91 |
+
|
92 |
+
First install the SetFit library:
|
93 |
+
|
94 |
+
```bash
|
95 |
+
pip install setfit
|
96 |
+
```
|
97 |
+
|
98 |
+
Then you can load this model and run inference.
|
99 |
+
|
100 |
+
```python
|
101 |
+
from setfit import SetFitModel
|
102 |
+
|
103 |
+
# Download from the 🤗 Hub
|
104 |
+
model = SetFitModel.from_pretrained("HelgeKn/SemEval-multi-class-8")
|
105 |
+
# Run inference
|
106 |
+
preds = model("To break the uncomfortable silence , Haney began to talk . ")
|
107 |
+
```
|
108 |
+
|
109 |
+
<!--
|
110 |
+
### Downstream Use
|
111 |
+
|
112 |
+
*List how someone could finetune this model on their own dataset.*
|
113 |
+
-->
|
114 |
+
|
115 |
+
<!--
|
116 |
+
### Out-of-Scope Use
|
117 |
+
|
118 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
119 |
+
-->
|
120 |
+
|
121 |
+
<!--
|
122 |
+
## Bias, Risks and Limitations
|
123 |
+
|
124 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
125 |
+
-->
|
126 |
+
|
127 |
+
<!--
|
128 |
+
### Recommendations
|
129 |
+
|
130 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
131 |
+
-->
|
132 |
+
|
133 |
+
## Training Details
|
134 |
+
|
135 |
+
### Training Set Metrics
|
136 |
+
| Training set | Min | Median | Max |
|
137 |
+
|:-------------|:----|:-------|:----|
|
138 |
+
| Word count | 4 | 27.0 | 74 |
|
139 |
+
|
140 |
+
| Label | Training Sample Count |
|
141 |
+
|:------|:----------------------|
|
142 |
+
| 0 | 8 |
|
143 |
+
| 1 | 8 |
|
144 |
+
| 2 | 8 |
|
145 |
+
| 3 | 8 |
|
146 |
+
| 4 | 8 |
|
147 |
+
| 5 | 8 |
|
148 |
+
| 6 | 8 |
|
149 |
+
|
150 |
+
### Training Hyperparameters
|
151 |
+
- batch_size: (16, 16)
|
152 |
+
- num_epochs: (2, 2)
|
153 |
+
- max_steps: -1
|
154 |
+
- sampling_strategy: oversampling
|
155 |
+
- num_iterations: 20
|
156 |
+
- body_learning_rate: (2e-05, 2e-05)
|
157 |
+
- head_learning_rate: 2e-05
|
158 |
+
- loss: CosineSimilarityLoss
|
159 |
+
- distance_metric: cosine_distance
|
160 |
+
- margin: 0.25
|
161 |
+
- end_to_end: False
|
162 |
+
- use_amp: False
|
163 |
+
- warmup_proportion: 0.1
|
164 |
+
- seed: 42
|
165 |
+
- eval_max_steps: -1
|
166 |
+
- load_best_model_at_end: False
|
167 |
+
|
168 |
+
### Training Results
|
169 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
170 |
+
|:------:|:----:|:-------------:|:---------------:|
|
171 |
+
| 0.0071 | 1 | 0.2786 | - |
|
172 |
+
| 0.3571 | 50 | 0.1703 | - |
|
173 |
+
| 0.7143 | 100 | 0.0932 | - |
|
174 |
+
| 1.0714 | 150 | 0.0173 | - |
|
175 |
+
| 1.4286 | 200 | 0.0048 | - |
|
176 |
+
| 1.7857 | 250 | 0.0024 | - |
|
177 |
+
|
178 |
+
### Framework Versions
|
179 |
+
- Python: 3.9.13
|
180 |
+
- SetFit: 1.0.1
|
181 |
+
- Sentence Transformers: 2.2.2
|
182 |
+
- Transformers: 4.36.0
|
183 |
+
- PyTorch: 2.1.1+cpu
|
184 |
+
- Datasets: 2.15.0
|
185 |
+
- Tokenizers: 0.15.0
|
186 |
+
|
187 |
+
## Citation
|
188 |
+
|
189 |
+
### BibTeX
|
190 |
+
```bibtex
|
191 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
192 |
+
doi = {10.48550/ARXIV.2209.11055},
|
193 |
+
url = {https://arxiv.org/abs/2209.11055},
|
194 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
195 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
196 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
197 |
+
publisher = {arXiv},
|
198 |
+
year = {2022},
|
199 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
200 |
+
}
|
201 |
+
```
|
202 |
+
|
203 |
+
<!--
|
204 |
+
## Glossary
|
205 |
+
|
206 |
+
*Clearly define terms in order to be accessible across audiences.*
|
207 |
+
-->
|
208 |
+
|
209 |
+
<!--
|
210 |
+
## Model Card Authors
|
211 |
+
|
212 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
213 |
+
-->
|
214 |
+
|
215 |
+
<!--
|
216 |
+
## Model Card Contact
|
217 |
+
|
218 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
219 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "C:\\Users\\Man_f/.cache\\torch\\sentence_transformers\\sentence-transformers_paraphrase-mpnet-base-v2\\",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.36.0",
|
23 |
+
"vocab_size": 30527
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
}
|
7 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": null,
|
3 |
+
"normalize_embeddings": false
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:097ca2f46f3d0d394109a452695ebd5766deaf93f079a14436f7dd20f922fea6
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8b3623ce1645ef4a097073a2d4e3795f519c0db15c4b097ac9bc782ed54ecd1
|
3 |
+
size 23052
|
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": false,
|
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": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
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": false,
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"104": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"30526": {
|
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 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": true,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"strip_accents": null,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "MPNetTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|