Add SetFit model
Browse files- 1_Pooling/config.json +9 -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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
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: Blockbuster Cuts Online Price, Challenges Netflix (Reuters) Reuters - Video
|
12 |
+
chain Blockbuster Inc on\Friday said it would lower the price of its online DVD
|
13 |
+
rentals\to undercut a similar move by Netflix Inc. that sparked a stock\a sell-off
|
14 |
+
of both companies' shares.
|
15 |
+
- text: Goss Gets Senate Panel's OK for CIA Post (AP) AP - A Senate panel on Tuesday
|
16 |
+
approved the nomination of Rep. Porter Goss, R-Fla., to head the CIA, overcoming
|
17 |
+
Democrats' objections that Goss was too political for the job.
|
18 |
+
- text: 'Crazy Like a Firefox Today, the Mozilla Foundation #39;s Firefox browser
|
19 |
+
officially launched -- welcome, version 1.0. In a way, it #39;s much ado about
|
20 |
+
nothing, seeing how it wasn #39;t that long ago that we reported on how Mozilla
|
21 |
+
had set '
|
22 |
+
- text: North Korea eases tough stance against US in nuclear talks North Korea on
|
23 |
+
Friday eased its tough stance against the United States, saying it is willing
|
24 |
+
to resume stalled six-way talks on its nuclear weapons if Washington is ready
|
25 |
+
to consider its demands.
|
26 |
+
- text: Mauresmo confident of LA victory Amelie Mauresmo insists she can win the Tour
|
27 |
+
Championships this week and finish the year as world number one. The Frenchwoman
|
28 |
+
could overtake Lindsay Davenport with a win in Los Angeles.
|
29 |
+
pipeline_tag: text-classification
|
30 |
+
inference: true
|
31 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
32 |
+
model-index:
|
33 |
+
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
34 |
+
results:
|
35 |
+
- task:
|
36 |
+
type: text-classification
|
37 |
+
name: Text Classification
|
38 |
+
dataset:
|
39 |
+
name: Unknown
|
40 |
+
type: unknown
|
41 |
+
split: test
|
42 |
+
metrics:
|
43 |
+
- type: accuracy
|
44 |
+
value: 0.83
|
45 |
+
name: Accuracy
|
46 |
+
---
|
47 |
+
|
48 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
49 |
+
|
50 |
+
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 [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
51 |
+
|
52 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
53 |
+
|
54 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
55 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
56 |
+
|
57 |
+
## Model Details
|
58 |
+
|
59 |
+
### Model Description
|
60 |
+
- **Model Type:** SetFit
|
61 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
62 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
63 |
+
- **Maximum Sequence Length:** 512 tokens
|
64 |
+
- **Number of Classes:** 4 classes
|
65 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
66 |
+
<!-- - **Language:** Unknown -->
|
67 |
+
<!-- - **License:** Unknown -->
|
68 |
+
|
69 |
+
### Model Sources
|
70 |
+
|
71 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
72 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
73 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
74 |
+
|
75 |
+
### Model Labels
|
76 |
+
| Label | Examples |
|
77 |
+
|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
78 |
+
| 1 | <ul><li>"Bills' patience paying off The savior? The Buffalo Bills have always thought so. Bills general manager and president Tom Donahoe believed if the organization was patient in waiting for Willis McGahee's rebuilt knee to respond, he would be a huge success."</li><li>'NHL Rejects Union Plan, Talks End Without Contract (Update2) Contract talks broke off today between the National Hockey League and its locked-out players union, leaving the sport a step closer to wiping out its whole season.'</li><li>'Veteran guard Black bugs opponents The Connecticut Sun have the quot;Tasmanian Devil quot; on their side as they enter the WNBA Finals tonight. quot;Well, you know, I play a lot like that; I #39;m kind of '</li></ul> |
|
79 |
+
| 2 | <ul><li>'IBM Reassures Workers After Milestone China Deal During an IBM employee meeting here Wednesday, a worker got up and asked a question that perhaps only 10 years ago would have been unthinkable: If he wanted '</li><li>'Fiat, GM struggle to settle row over Fiat Auto sale option MILAN (AFP) - Top officials from Fiat of Italy and General Motors were conferring in a bid to settle differences on Fiat #39;s option to sell its loss-making car operation to the US auto giant, a dispute that threatens their four-year-old collaboration.'</li><li>'Transco sells four gas networks National Grid Transco has sold half of its gas distribution networks for 5.8bn (\\$10.4bn), it was announced today. The move has been welcomed by the gas and electricity regulator Ofgem, which said new competition in the sector could lower prices.'</li></ul> |
|
80 |
+
| 0 | <ul><li>'Unit Refused Iraq Mission, Military Says WASHINGTON - Relatives of soldiers who refused to deliver supplies in Iraq say the troops considered the mission too dangerous, in part because their vehicles were in poor shape. The Army is investigating up to 19 reservist members of a platoon that is part of the 343rd Quartermaster Company, based in Rock Hill, S.C...'</li><li>"Phelps, Thorpe Advance in 200 Freestyle ATHENS, Greece - Michael Phelps took care of qualifying for the Olympic 200-meter freestyle semifinals Sunday, and then found out he had been added to the American team for the evening's 400 freestyle relay final. Phelps' rivals Ian Thorpe and Pieter van den Hoogenband and teammate Klete Keller were faster than the teenager in the 200 free preliminaries..."</li><li>'Iranian Hard-Liners Criticize Nuclear Deal (AP) AP - Iranian hard-liners on Tuesday criticized a nuclear deal reached with European nations, saying Iran gained nothing in return for suspending the nuclear enrichment process.'</li></ul> |
|
81 |
+
| 3 | <ul><li>'Intel test chip boasts technology to add to speed Intel, the world #39;s biggest semiconductor maker, said Monday it built a test chip with a new process that creates faster circuits by packing 10 million transistors into an area the size of the tip of a ballpoint pen.'</li><li>"Sybase releases free Express database for Linux The company is releasing its new ASE Express Edition for free in hopes of attracting customers who will later upgrade to Sybase's ASE Small Business Edition."</li><li>'Google, 5 big libraries team to offer books Google Inc. has partnered with five of the world #39;s leading libraries, including those at Stanford and Harvard, to digitally scan their collections so that the books can be searched, and in many cases read, online free of charge.'</li></ul> |
|
82 |
+
|
83 |
+
## Evaluation
|
84 |
+
|
85 |
+
### Metrics
|
86 |
+
| Label | Accuracy |
|
87 |
+
|:--------|:---------|
|
88 |
+
| **all** | 0.83 |
|
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("vidhi0206/setfit-paraphrase-mpnet-ag_news_v2")
|
107 |
+
# Run inference
|
108 |
+
preds = model("Mauresmo confident of LA victory Amelie Mauresmo insists she can win the Tour Championships this week and finish the year as world number one. The Frenchwoman could overtake Lindsay Davenport with a win in Los Angeles.")
|
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 | 15 | 37.375 | 64 |
|
141 |
+
|
142 |
+
| Label | Training Sample Count |
|
143 |
+
|:------|:----------------------|
|
144 |
+
| 0 | 16 |
|
145 |
+
| 1 | 16 |
|
146 |
+
| 2 | 16 |
|
147 |
+
| 3 | 16 |
|
148 |
+
|
149 |
+
### Training Hyperparameters
|
150 |
+
- batch_size: (8, 8)
|
151 |
+
- num_epochs: (1, 1)
|
152 |
+
- max_steps: -1
|
153 |
+
- sampling_strategy: oversampling
|
154 |
+
- num_iterations: 20
|
155 |
+
- body_learning_rate: (2e-05, 2e-05)
|
156 |
+
- head_learning_rate: 2e-05
|
157 |
+
- loss: CosineSimilarityLoss
|
158 |
+
- distance_metric: cosine_distance
|
159 |
+
- margin: 0.25
|
160 |
+
- end_to_end: False
|
161 |
+
- use_amp: False
|
162 |
+
- warmup_proportion: 0.1
|
163 |
+
- seed: 42
|
164 |
+
- eval_max_steps: -1
|
165 |
+
- load_best_model_at_end: False
|
166 |
+
|
167 |
+
### Training Results
|
168 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
169 |
+
|:------:|:----:|:-------------:|:---------------:|
|
170 |
+
| 0.0031 | 1 | 0.4374 | - |
|
171 |
+
| 0.1562 | 50 | 0.1774 | - |
|
172 |
+
| 0.3125 | 100 | 0.0287 | - |
|
173 |
+
| 0.4688 | 150 | 0.0008 | - |
|
174 |
+
| 0.625 | 200 | 0.0006 | - |
|
175 |
+
| 0.7812 | 250 | 0.0002 | - |
|
176 |
+
| 0.9375 | 300 | 0.0004 | - |
|
177 |
+
|
178 |
+
### Framework Versions
|
179 |
+
- Python: 3.8.10
|
180 |
+
- SetFit: 1.0.3
|
181 |
+
- Sentence Transformers: 2.3.1
|
182 |
+
- Transformers: 4.37.2
|
183 |
+
- PyTorch: 2.2.0+cu121
|
184 |
+
- Datasets: 2.17.0
|
185 |
+
- Tokenizers: 0.15.1
|
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": "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": "4.37.2",
|
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 |
+
"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 sha256:50b122c0a8dfe220442d424b596f8e52e0208c4487833f85f068816b47bc3c5e
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d5e643a45e5f751952cf7aa409a5add0371b5033f1be6cdeea93930151af249
|
3 |
+
size 25463
|
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": false,
|
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": false,
|
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
|
|