khang119966 commited on
Commit
dcfa973
1 Parent(s): 3cf3d90

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -8,7 +8,7 @@ widget:
8
  - text: "hag quảg <mask> kực nét"
9
  ---
10
 
11
- # 5CD-AI/visobert-14gb-corpus-pretrained
12
  ## Overview
13
  <!-- Provide a quick summary of what the model is/does. -->
14
  We continually pretrain `uitnlp/visobert` on a merged 14GB dataset for 5 epochs, the training dataset includes:
@@ -121,7 +121,7 @@ Here are the results on 4 downstream tasks on Vietnamese social media texts, inc
121
  <td>86.8</td>
122
  </tr>
123
  <tr align="center">
124
- <td align="left">visobert-14gb-corpus-pretrained</td>
125
  <td>82.2</td>
126
  <td>68.69</td>
127
  <td>68.75</td>
@@ -166,7 +166,7 @@ Then you can use this model for fill-mask task like this:
166
  ```python
167
  from transformers import pipeline
168
 
169
- model_path = "5CD-AI/visobert-14gb-corpus-pretrained"
170
  mask_filler = pipeline("fill-mask", model_path)
171
 
172
  mask_filler("ăn nói xà <mask>", top_k=10)
 
8
  - text: "hag quảg <mask> kực nét"
9
  ---
10
 
11
+ # 5CD-AI/visobert-14gb-corpus
12
  ## Overview
13
  <!-- Provide a quick summary of what the model is/does. -->
14
  We continually pretrain `uitnlp/visobert` on a merged 14GB dataset for 5 epochs, the training dataset includes:
 
121
  <td>86.8</td>
122
  </tr>
123
  <tr align="center">
124
+ <td align="left">visobert-14gb-corpus</td>
125
  <td>82.2</td>
126
  <td>68.69</td>
127
  <td>68.75</td>
 
166
  ```python
167
  from transformers import pipeline
168
 
169
+ model_path = "5CD-AI/visobert-14gb-corpus"
170
  mask_filler = pipeline("fill-mask", model_path)
171
 
172
  mask_filler("ăn nói xà <mask>", top_k=10)