Commit
•
85318c5
1
Parent(s):
b07ae5f
Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +237 -0
- config.json +31 -0
- config_sentence_transformers.json +9 -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
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Now that the baffling, elongated, hyperreal coronation has occurred—no, not
|
12 |
+
that one—and Liz Truss has become Prime Minister, a degree of intervention and
|
13 |
+
action on energy bills has emerged, ahead of the looming socioeconomic catastrophe
|
14 |
+
facing the country this winter.
|
15 |
+
- text: But it needs to go much further.
|
16 |
+
- text: What could possibly go wrong?
|
17 |
+
- text: If you are White you might feel bad about hurting others or you might feel
|
18 |
+
afraid to lose this privilege….Overcoming White privilege is a job that must start
|
19 |
+
with the White community….
|
20 |
+
- text: '[JF: Obviously, immigration wasn’t stopped: the current population of the
|
21 |
+
United States is 329.5 million—it passed 300 million in 2006.'
|
22 |
+
pipeline_tag: text-classification
|
23 |
+
inference: true
|
24 |
+
model-index:
|
25 |
+
- name: SetFit
|
26 |
+
results:
|
27 |
+
- task:
|
28 |
+
type: text-classification
|
29 |
+
name: Text Classification
|
30 |
+
dataset:
|
31 |
+
name: Unknown
|
32 |
+
type: unknown
|
33 |
+
split: test
|
34 |
+
metrics:
|
35 |
+
- type: accuracy
|
36 |
+
value: 0.7736625514403292
|
37 |
+
name: Accuracy
|
38 |
+
---
|
39 |
+
|
40 |
+
# SetFit
|
41 |
+
|
42 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A LinearSVC instance is used for classification.
|
43 |
+
|
44 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
45 |
+
|
46 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
47 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
48 |
+
|
49 |
+
## Model Details
|
50 |
+
|
51 |
+
### Model Description
|
52 |
+
- **Model Type:** SetFit
|
53 |
+
<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
|
54 |
+
- **Classification head:** a LinearSVC instance
|
55 |
+
- **Maximum Sequence Length:** 512 tokens
|
56 |
+
- **Number of Classes:** 2 classes
|
57 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
58 |
+
<!-- - **Language:** Unknown -->
|
59 |
+
<!-- - **License:** Unknown -->
|
60 |
+
|
61 |
+
### Model Sources
|
62 |
+
|
63 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
64 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
65 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
66 |
+
|
67 |
+
### Model Labels
|
68 |
+
| Label | Examples |
|
69 |
+
|:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
70 |
+
| SUBJ | <ul><li>'Now suppose that under stress of abnormal public revenue the structure of government is somewhat rationalized and that by such means as economy and efficiency the cost of government by measure is much reduced.'</li><li>'Modern Russia is a propaganda state, but not in the same way as the Soviet Union.'</li><li>'The spender of public money will never want followers.'</li></ul> |
|
71 |
+
| OBJ | <ul><li>'But a top buying agent tells me that access to 13 can be gained if you know the right people.'</li><li>'“Normally, the majority opinion would speak for itself.” The decision is “really about policy—our state has values of inclusion and diversity.” The ruling is based “on policy, which is the definition of judicial activism.'</li><li>'asked American Federation of Teachers President Randi Weingarten.'</li></ul> |
|
72 |
+
|
73 |
+
## Evaluation
|
74 |
+
|
75 |
+
### Metrics
|
76 |
+
| Label | Accuracy |
|
77 |
+
|:--------|:---------|
|
78 |
+
| **all** | 0.7737 |
|
79 |
+
|
80 |
+
## Uses
|
81 |
+
|
82 |
+
### Direct Use for Inference
|
83 |
+
|
84 |
+
First install the SetFit library:
|
85 |
+
|
86 |
+
```bash
|
87 |
+
pip install setfit
|
88 |
+
```
|
89 |
+
|
90 |
+
Then you can load this model and run inference.
|
91 |
+
|
92 |
+
```python
|
93 |
+
from setfit import SetFitModel
|
94 |
+
|
95 |
+
# Download from the 🤗 Hub
|
96 |
+
model = SetFitModel.from_pretrained("SOUMYADEEPSAR/SetFit_SubjectivityDetection")
|
97 |
+
# Run inference
|
98 |
+
preds = model("What could possibly go wrong?")
|
99 |
+
```
|
100 |
+
|
101 |
+
<!--
|
102 |
+
### Downstream Use
|
103 |
+
|
104 |
+
*List how someone could finetune this model on their own dataset.*
|
105 |
+
-->
|
106 |
+
|
107 |
+
<!--
|
108 |
+
### Out-of-Scope Use
|
109 |
+
|
110 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
111 |
+
-->
|
112 |
+
|
113 |
+
<!--
|
114 |
+
## Bias, Risks and Limitations
|
115 |
+
|
116 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
117 |
+
-->
|
118 |
+
|
119 |
+
<!--
|
120 |
+
### Recommendations
|
121 |
+
|
122 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
123 |
+
-->
|
124 |
+
|
125 |
+
## Training Details
|
126 |
+
|
127 |
+
### Training Set Metrics
|
128 |
+
| Training set | Min | Median | Max |
|
129 |
+
|:-------------|:----|:-------|:----|
|
130 |
+
| Word count | 3 | 22.085 | 77 |
|
131 |
+
|
132 |
+
| Label | Training Sample Count |
|
133 |
+
|:------|:----------------------|
|
134 |
+
| OBJ | 100 |
|
135 |
+
| SUBJ | 100 |
|
136 |
+
|
137 |
+
### Training Hyperparameters
|
138 |
+
- batch_size: (32, 32)
|
139 |
+
- num_epochs: (3, 3)
|
140 |
+
- max_steps: -1
|
141 |
+
- sampling_strategy: oversampling
|
142 |
+
- body_learning_rate: (2e-05, 1e-05)
|
143 |
+
- head_learning_rate: 0.01
|
144 |
+
- loss: CosineSimilarityLoss
|
145 |
+
- distance_metric: cosine_distance
|
146 |
+
- margin: 0.25
|
147 |
+
- end_to_end: False
|
148 |
+
- use_amp: False
|
149 |
+
- warmup_proportion: 0.1
|
150 |
+
- seed: 42
|
151 |
+
- eval_max_steps: -1
|
152 |
+
- load_best_model_at_end: False
|
153 |
+
|
154 |
+
### Training Results
|
155 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
156 |
+
|:------:|:----:|:-------------:|:---------------:|
|
157 |
+
| 0.0016 | 1 | 0.2686 | - |
|
158 |
+
| 0.0791 | 50 | 0.2494 | - |
|
159 |
+
| 0.1582 | 100 | 0.2639 | - |
|
160 |
+
| 0.2373 | 150 | 0.2258 | - |
|
161 |
+
| 0.3165 | 200 | 0.0176 | - |
|
162 |
+
| 0.3956 | 250 | 0.0027 | - |
|
163 |
+
| 0.4747 | 300 | 0.0017 | - |
|
164 |
+
| 0.5538 | 350 | 0.0013 | - |
|
165 |
+
| 0.6329 | 400 | 0.0016 | - |
|
166 |
+
| 0.7120 | 450 | 0.001 | - |
|
167 |
+
| 0.7911 | 500 | 0.0009 | - |
|
168 |
+
| 0.8703 | 550 | 0.001 | - |
|
169 |
+
| 0.9494 | 600 | 0.001 | - |
|
170 |
+
| 1.0285 | 650 | 0.0009 | - |
|
171 |
+
| 1.1076 | 700 | 0.0008 | - |
|
172 |
+
| 1.1867 | 750 | 0.0008 | - |
|
173 |
+
| 1.2658 | 800 | 0.0006 | - |
|
174 |
+
| 1.3449 | 850 | 0.0007 | - |
|
175 |
+
| 1.4241 | 900 | 0.0006 | - |
|
176 |
+
| 1.5032 | 950 | 0.0007 | - |
|
177 |
+
| 1.5823 | 1000 | 0.0006 | - |
|
178 |
+
| 1.6614 | 1050 | 0.0005 | - |
|
179 |
+
| 1.7405 | 1100 | 0.0006 | - |
|
180 |
+
| 1.8196 | 1150 | 0.0007 | - |
|
181 |
+
| 1.8987 | 1200 | 0.0005 | - |
|
182 |
+
| 1.9778 | 1250 | 0.0006 | - |
|
183 |
+
| 2.0570 | 1300 | 0.0005 | - |
|
184 |
+
| 2.1361 | 1350 | 0.0005 | - |
|
185 |
+
| 2.2152 | 1400 | 0.0004 | - |
|
186 |
+
| 2.2943 | 1450 | 0.0005 | - |
|
187 |
+
| 2.3734 | 1500 | 0.0004 | - |
|
188 |
+
| 2.4525 | 1550 | 0.0004 | - |
|
189 |
+
| 2.5316 | 1600 | 0.0004 | - |
|
190 |
+
| 2.6108 | 1650 | 0.0004 | - |
|
191 |
+
| 2.6899 | 1700 | 0.0005 | - |
|
192 |
+
| 2.7690 | 1750 | 0.0005 | - |
|
193 |
+
| 2.8481 | 1800 | 0.0004 | - |
|
194 |
+
| 2.9272 | 1850 | 0.0005 | - |
|
195 |
+
|
196 |
+
### Framework Versions
|
197 |
+
- Python: 3.10.12
|
198 |
+
- SetFit: 1.0.3
|
199 |
+
- Sentence Transformers: 2.4.0
|
200 |
+
- Transformers: 4.37.2
|
201 |
+
- PyTorch: 2.1.0+cu121
|
202 |
+
- Datasets: 2.17.1
|
203 |
+
- Tokenizers: 0.15.2
|
204 |
+
|
205 |
+
## Citation
|
206 |
+
|
207 |
+
### BibTeX
|
208 |
+
```bibtex
|
209 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
210 |
+
doi = {10.48550/ARXIV.2209.11055},
|
211 |
+
url = {https://arxiv.org/abs/2209.11055},
|
212 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
213 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
214 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
215 |
+
publisher = {arXiv},
|
216 |
+
year = {2022},
|
217 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
218 |
+
}
|
219 |
+
```
|
220 |
+
|
221 |
+
<!--
|
222 |
+
## Glossary
|
223 |
+
|
224 |
+
*Clearly define terms in order to be accessible across audiences.*
|
225 |
+
-->
|
226 |
+
|
227 |
+
<!--
|
228 |
+
## Model Card Authors
|
229 |
+
|
230 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
231 |
+
-->
|
232 |
+
|
233 |
+
<!--
|
234 |
+
## Model Card Contact
|
235 |
+
|
236 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
237 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-small-en-v1.5",
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1536,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.37.2",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.28.1",
|
5 |
+
"pytorch": "1.13.0+cu117"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": [
|
3 |
+
"OBJ",
|
4 |
+
"SUBJ"
|
5 |
+
],
|
6 |
+
"normalize_embeddings": false
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db57d93df4c231a01f5fbea4cd7cdfe55f7b2500396ca6473afacc0345a8d07
|
3 |
+
size 133462128
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e317176e43ebfd70ba3fef050063c1c550e0041daa6c951f535c5d03aad5a9dc
|
3 |
+
size 3803
|
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": true
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|