htdung167 commited on
Commit
5961ad0
1 Parent(s): 06141f9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +159 -195
README.md CHANGED
@@ -3,199 +3,163 @@ library_name: transformers
3
  tags: []
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
  <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
200
-
201
-
 
3
  tags: []
4
  ---
5
 
6
+ # 5CD-AI/viso-twhin-bert-large
7
+ ## Overview
8
  <!-- Provide a quick summary of what the model is/does. -->
9
+ We reduce TwHIN-BERT's vocabulary size to 20k on the UIT dataset and continue pretraining for 10 epochs.
10
+
11
+ Here are the results on 4 downstream tasks on Vietnamese social media texts, including Emotion Recognition(UIT-VSMEC), Hate Speech Detection(UIT-HSD), Spam Reviews Detection(ViSpamReviews), Hate Speech Spans Detection(ViHOS):
12
+ <table>
13
+ <tr align="center">
14
+ <td rowspan=2><b>Model</td>
15
+ <td rowspan=2><b>Avg</td>
16
+ <td colspan=3><b>Emotion Recognition</td>
17
+ <td colspan=3><b>Hate Speech Detection</td>
18
+ <td colspan=3><b>Spam Reviews Detection</td>
19
+ <td colspan=3><b>Hate Speech Spans Detection</td>
20
+ </tr>
21
+ <tr align="center">
22
+ <td><b>Acc</td>
23
+ <td><b>WF1</td>
24
+ <td><b>MF1</td>
25
+ <td><b>Acc</td>
26
+ <td><b>WF1</td>
27
+ <td><b>MF1</td>
28
+ <td><b>Acc</td>
29
+ <td><b>WF1</td>
30
+ <td><b>MF1</td>
31
+ <td><b>Acc</td>
32
+ <td><b>WF1</td>
33
+ <td><b>MF1</td>
34
+ </tr>
35
+ <tr align="center">
36
+ <td align="left">viBERT</td>
37
+ <td>78.16</td>
38
+ <td>61.91</td>
39
+ <td>61.98</td>
40
+ <td>59.7</td>
41
+ <td>85.34</td>
42
+ <td>85.01</td>
43
+ <td>62.07</td>
44
+ <td>89.93</td>
45
+ <td>89.79</td>
46
+ <td>76.8</td>
47
+ <td>90.42</td>
48
+ <td>90.45</td>
49
+ <td>84.55</td>
50
+ </tr>
51
+ <tr align="center">
52
+ <td align="left">vELECTRA</td>
53
+ <td>79.23</td>
54
+ <td>64.79</td>
55
+ <td>64.71</td>
56
+ <td>61.95</td>
57
+ <td>86.96</td>
58
+ <td>86.37</td>
59
+ <td>63.95</td>
60
+ <td>89.83</td>
61
+ <td>89.68</td>
62
+ <td>76.23</td>
63
+ <td>90.59</td>
64
+ <td>90.58</td>
65
+ <td>85.12</td>
66
+ </tr>
67
+ <tr align="center">
68
+ <td align="left">PhoBERT-Base </td>
69
+ <td>79.3</td>
70
+ <td>63.49</td>
71
+ <td>63.36</td>
72
+ <td>61.41</td>
73
+ <td>87.12</td>
74
+ <td>86.81</td>
75
+ <td>65.01</td>
76
+ <td>89.83</td>
77
+ <td>89.75</td>
78
+ <td>76.18</td>
79
+ <td>91.32</td>
80
+ <td>91.38</td>
81
+ <td>85.92</td>
82
+ </tr>
83
+ <tr align="center">
84
+ <td align="left">PhoBERT-Large</td>
85
+ <td>79.82</td>
86
+ <td>64.71</td>
87
+ <td>64.66</td>
88
+ <td>62.55</td>
89
+ <td>87.32</td>
90
+ <td>86.98</td>
91
+ <td>65.14</td>
92
+ <td>90.12</td>
93
+ <td>90.03</td>
94
+ <td>76.88</td>
95
+ <td>91.44</td>
96
+ <td>91.46</td>
97
+ <td>86.56</td>
98
+ </tr>
99
+ <tr align="center">
100
+ <td align="left">ViSoBERT</td>
101
+ <td>81.58</td>
102
+ <td>68.1</td>
103
+ <td>68.37</td>
104
+ <td>65.88</td>
105
+ <td>88.51</td>
106
+ <td>88.31</td>
107
+ <td>68.77</td>
108
+ <td>90.99</td>
109
+ <td>90.92</td>
110
+ <td>79.06</td>
111
+ <td>91.62</td>
112
+ <td>91.57</td>
113
+ <td>86.8</td>
114
+ </tr>
115
+ <tr align="center">
116
+ <td align="left">visobert-14gb-corpus-pretrained</td>
117
+ <td>82.2</td>
118
+ <td>68.69</td>
119
+ <td>68.75</td>
120
+ <td>66.03</td>
121
+ <td>88.79</td>
122
+ <td>88.6</td>
123
+ <td>69.57</td>
124
+ <td>91.02</td>
125
+ <td>90.88</td>
126
+ <td>77.13</td>
127
+ <td>93.69</td>
128
+ <td>93.63</td>
129
+ <td>89.66</td>
130
+ </tr>
131
+ <tr align="center">
132
+ <td align="left">viso-twhin-bert-large</td>
133
+ <td><b>83.87</td>
134
+ <td><b>73.45</td>
135
+ <td><b>73.14</td>
136
+ <td><b>70.99</td>
137
+ <td><b>88.86</td>
138
+ <td><b>88.8</td>
139
+ <td><b>70.81</td>
140
+ <td><b>91.6</td>
141
+ <td><b>91.47</td>
142
+ <td><b>79.07</td>
143
+ <td><b>94.08</td>
144
+ <td><b>93.96</td>
145
+ <td><b>90.22</td>
146
+ </tr>
147
+ </div>
148
+ </table>
149
+
150
+ ## Usage (HuggingFace Transformers)
151
+
152
+ Install `transformers` package:
153
+
154
+ pip install transformers
155
+
156
+ Then you can use this model for fill-mask task like this:
157
+
158
+ ```python
159
+ from transformers import pipeline
160
+
161
+ model_path = "5CD-AI/visobert-14gb-corpus-pretrained"
162
+ mask_filler = pipeline("fill-mask", model_path)
163
+
164
+ mask_filler("ăn nói xà <mask>", top_k=10)
165
+ ```