ehsanhallo
commited on
Commit
·
fccd4ae
1
Parent(s):
e3c89ff
Add SetFit model
Browse files- .gitattributes +2 -0
- 1_Pooling/config.json +7 -0
- README.md +237 -0
- config.json +26 -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 +3 -0
- tokenizer_config.json +64 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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
|
37 |
+
unigram.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 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: ' i still dont know what we would do though'
|
12 |
+
- text: ' where`d you go!'
|
13 |
+
- text: ' Thank you! I`m working on `s'
|
14 |
+
- text: Terminator Salvation... by myself.
|
15 |
+
- text: ' lol man i got 2 1 /2 hrs an iont how i woulda made it wit out my ramen noodles
|
16 |
+
and t.v. Time'
|
17 |
+
pipeline_tag: text-classification
|
18 |
+
inference: true
|
19 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
20 |
+
model-index:
|
21 |
+
- name: SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
22 |
+
results:
|
23 |
+
- task:
|
24 |
+
type: text-classification
|
25 |
+
name: Text Classification
|
26 |
+
dataset:
|
27 |
+
name: Unknown
|
28 |
+
type: unknown
|
29 |
+
split: test
|
30 |
+
metrics:
|
31 |
+
- type: accuracy
|
32 |
+
value: 0.77
|
33 |
+
name: Accuracy
|
34 |
+
---
|
35 |
+
|
36 |
+
# SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
37 |
+
|
38 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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.
|
39 |
+
|
40 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
41 |
+
|
42 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
43 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
44 |
+
|
45 |
+
## Model Details
|
46 |
+
|
47 |
+
### Model Description
|
48 |
+
- **Model Type:** SetFit
|
49 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
|
50 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
51 |
+
- **Maximum Sequence Length:** 128 tokens
|
52 |
+
- **Number of Classes:** 3 classes
|
53 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
54 |
+
<!-- - **Language:** Unknown -->
|
55 |
+
<!-- - **License:** Unknown -->
|
56 |
+
|
57 |
+
### Model Sources
|
58 |
+
|
59 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
60 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
61 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
62 |
+
|
63 |
+
### Model Labels
|
64 |
+
| Label | Examples |
|
65 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
66 |
+
| 0 | <ul><li>'چه سودایی که سر همینا از دست دادم😂'</li><li>'خو فارسی بنویس بفهمه 😂😂😂😂😂'</li><li>'اینجا ایران همین سایتا هم\u200cزیادی..نیازی به بررسی ندارن...کلا دوسداریم به همچی ایراد بگیریم.'</li></ul> |
|
67 |
+
| 1 | <ul><li>'کد کارت مشکی NHKDKI'</li><li>'اتفاقا مسیولیت بیشتری برات میاره و درگیریات بیشتر میشه برای هدفی که داری'</li><li>'من میخام شروع کنم،اورج بفروشم یا فیک؟فیک ارزونتره ولی فیکه.اورجینال هم ک گرون تره ؟بنظرت اورج میخرن؟؟'</li></ul> |
|
68 |
+
| 2 | <ul><li>'🔥🔥🔥🔥'</li><li>'😂😂😂'</li><li>'چه قدر عالی وخفن 🔥🔥'</li></ul> |
|
69 |
+
|
70 |
+
## Evaluation
|
71 |
+
|
72 |
+
### Metrics
|
73 |
+
| Label | Accuracy |
|
74 |
+
|:--------|:---------|
|
75 |
+
| **all** | 0.77 |
|
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("ehsanhallo/setfit-paraphrase-multilingual-MiniLM-L12-v2-ig-fa")
|
94 |
+
# Run inference
|
95 |
+
preds = model(" where`d you go!")
|
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 | 1 | 7.0 | 75 |
|
128 |
+
|
129 |
+
| Label | Training Sample Count |
|
130 |
+
|:------|:----------------------|
|
131 |
+
| 0 | 31 |
|
132 |
+
| 1 | 131 |
|
133 |
+
| 2 | 364 |
|
134 |
+
|
135 |
+
### Training Hyperparameters
|
136 |
+
- batch_size: (32, 16)
|
137 |
+
- num_epochs: (2, 4)
|
138 |
+
- max_steps: -1
|
139 |
+
- sampling_strategy: oversampling
|
140 |
+
- body_learning_rate: (2e-05, 5e-06)
|
141 |
+
- head_learning_rate: 0.002
|
142 |
+
- loss: CosineSimilarityLoss
|
143 |
+
- distance_metric: cosine_distance
|
144 |
+
- margin: 0.25
|
145 |
+
- end_to_end: False
|
146 |
+
- use_amp: False
|
147 |
+
- warmup_proportion: 0.1
|
148 |
+
- l2_weight: 0.01
|
149 |
+
- seed: 42
|
150 |
+
- eval_max_steps: -1
|
151 |
+
- load_best_model_at_end: True
|
152 |
+
|
153 |
+
### Training Results
|
154 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
155 |
+
|:----------:|:--------:|:-------------:|:---------------:|
|
156 |
+
| 0.0002 | 1 | 0.1854 | - |
|
157 |
+
| 0.0529 | 250 | 0.0626 | - |
|
158 |
+
| 0.1058 | 500 | 0.0034 | 0.2484 |
|
159 |
+
| 0.1588 | 750 | 0.0029 | - |
|
160 |
+
| 0.2117 | 1000 | 0.001 | 0.1899 |
|
161 |
+
| 0.2646 | 1250 | 0.0001 | - |
|
162 |
+
| **0.3175** | **1500** | **0.0001** | **0.1849** |
|
163 |
+
| 0.3704 | 1750 | 0.0001 | - |
|
164 |
+
| 0.4234 | 2000 | 0.0001 | 0.1876 |
|
165 |
+
| 0.4763 | 2250 | 0.0001 | - |
|
166 |
+
| 0.5292 | 2500 | 0.0 | 0.1888 |
|
167 |
+
| 0.5821 | 2750 | 0.0001 | - |
|
168 |
+
| 0.6351 | 3000 | 0.0 | 0.1885 |
|
169 |
+
| 0.6880 | 3250 | 0.0 | - |
|
170 |
+
| 0.7409 | 3500 | 0.0 | 0.1915 |
|
171 |
+
| 0.7938 | 3750 | 0.0 | - |
|
172 |
+
| 0.8467 | 4000 | 0.0 | 0.1947 |
|
173 |
+
| 0.8997 | 4250 | 0.0 | - |
|
174 |
+
| 0.9526 | 4500 | 0.0 | 0.1986 |
|
175 |
+
| 1.0055 | 4750 | 0.0 | - |
|
176 |
+
| 1.0584 | 5000 | 0.0 | 0.207 |
|
177 |
+
| 1.1113 | 5250 | 0.0 | - |
|
178 |
+
| 1.1643 | 5500 | 0.0 | 0.2078 |
|
179 |
+
| 1.2172 | 5750 | 0.0 | - |
|
180 |
+
| 1.2701 | 6000 | 0.0 | 0.2096 |
|
181 |
+
| 1.3230 | 6250 | 0.0 | - |
|
182 |
+
| 1.3760 | 6500 | 0.0 | 0.2095 |
|
183 |
+
| 1.4289 | 6750 | 0.0 | - |
|
184 |
+
| 1.4818 | 7000 | 0.0 | 0.2103 |
|
185 |
+
| 1.5347 | 7250 | 0.0 | - |
|
186 |
+
| 1.5876 | 7500 | 0.0 | 0.2133 |
|
187 |
+
| 1.6406 | 7750 | 0.0 | - |
|
188 |
+
| 1.6935 | 8000 | 0.0 | 0.2154 |
|
189 |
+
| 1.7464 | 8250 | 0.0 | - |
|
190 |
+
| 1.7993 | 8500 | 0.0 | 0.2141 |
|
191 |
+
| 1.8522 | 8750 | 0.0 | - |
|
192 |
+
| 1.9052 | 9000 | 0.0 | 0.2141 |
|
193 |
+
| 1.9581 | 9250 | 0.0 | - |
|
194 |
+
|
195 |
+
* The bold row denotes the saved checkpoint.
|
196 |
+
### Framework Versions
|
197 |
+
- Python: 3.10.12
|
198 |
+
- SetFit: 1.0.1
|
199 |
+
- Sentence Transformers: 2.2.2
|
200 |
+
- Transformers: 4.35.2
|
201 |
+
- PyTorch: 2.1.0+cu121
|
202 |
+
- Datasets: 2.16.1
|
203 |
+
- Tokenizers: 0.15.0
|
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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/sentiment/train_output/step_1500/",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
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": "2.0.0",
|
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 sha256:2427ed2a40bad5f431b7d4d1fb03e42470b0cc80973c78b6f95fc9f51c37c804
|
3 |
+
size 470637416
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fab1dbb593ba765d69bc7cc97e81932a089bcf4f98f972ba79f9227585bb1a5c
|
3 |
+
size 10095
|
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": 128,
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa685fc160bbdbab64058d4fc91b60e62d207e8dc60b9af5c002c5ab946ded00
|
3 |
+
size 17083009
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"max_length": 128,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "</s>",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|