up201806461 commited on
Commit
9d9de71
1 Parent(s): d7b2b8c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +194 -0
README.md ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - code
4
+ metrics:
5
+ - perplexity
6
+ library_name: transformers
7
+ pipeline_tag: fill-mask
8
+ tags:
9
+ - MLM
10
+ ---
11
+ # Model Card for Model ID
12
+
13
+ A BERT-like model pre-trained on Java buggy code.
14
+
15
+ ## Model Details
16
+
17
+ ### Model Description
18
+
19
+ A BERT-like model pre-trained on Java buggy code.
20
+
21
+ - **Developed by:** André Nascimento
22
+ - **Shared by:** Hugging Face
23
+ - **Model type:** Fill-Mask
24
+ - **Language(s) (NLP):** Java (EN)
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model:** [BERT Base Uncased](https://huggingface.co/bert-base-cased)
27
+
28
+ ## Uses
29
+
30
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
31
+
32
+ ### Direct Use
33
+
34
+ Fill-Mask.
35
+
36
+ [More Information Needed]
37
+
38
+ ### Downstream Use [optional]
39
+
40
+ The model can be used for other tasks, like Text Classification.
41
+
42
+ ### Out-of-Scope Use
43
+
44
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ## Bias, Risks, and Limitations
49
+
50
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Recommendations
55
+
56
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
57
+
58
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
59
+
60
+ ## How to Get Started with the Model
61
+
62
+ Use the code below to get started with the model.
63
+
64
+ ```python
65
+ from transformers import pipeline
66
+ unmasker = pipeline('fill-mask', model='bert-base-cased')
67
+ unmasker(java_code) # Replace with Java code; Use '[MASK]' to mask tokens/words in the code.
68
+ ```
69
+
70
+ [More Information Needed]
71
+
72
+ ## Training Details
73
+
74
+ ### Training Data
75
+
76
+ The model was trained on 236040 Java methods, containing the code before and after the bug fix was applied. The whole dataset was built from [Extracted Bug-Fix Pairs (BFP)](https://sites.google.com/view/learning-fixes/data#h.p_RNvM6OfOYBMI), extracting single file/single method commits, and keeping only method with less than 512 tokens. An 80/20 train/validation split was applied afterwards.
77
+
78
+ ### Training Procedure
79
+
80
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
81
+
82
+ #### Preprocessing [optional]
83
+
84
+ Remove comments and replace consecutive whitespace characters by a single space
85
+
86
+ #### Training Hyperparameters
87
+
88
+ - **Training regime:** fp16 mixed precision <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
89
+
90
+ #### Speeds, Sizes, Times [optional]
91
+
92
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
93
+
94
+ [More Information Needed]
95
+
96
+ ## Evaluation
97
+
98
+ <!-- This section describes the evaluation protocols and provides the results. -->
99
+
100
+ ### Testing Data, Factors & Metrics
101
+
102
+ #### Testing Data
103
+
104
+ The model was evaluated on 59024 Java methods, from the 20% split of the dataset mentioned in [Training Data](#training-data)
105
+
106
+ [More Information Needed]
107
+
108
+ #### Factors
109
+
110
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Metrics
115
+
116
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
117
+
118
+ [More Information Needed]
119
+
120
+ ### Results
121
+
122
+ [More Information Needed]
123
+
124
+ #### Summary
125
+
126
+
127
+
128
+ ## Model Examination [optional]
129
+
130
+ <!-- Relevant interpretability work for the model goes here -->
131
+
132
+ [More Information Needed]
133
+
134
+ ## Environmental Impact
135
+
136
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
137
+
138
+ 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).
139
+
140
+ - **Hardware Type:** [More Information Needed]
141
+ - **Hours used:** [More Information Needed]
142
+ - **Cloud Provider:** [More Information Needed]
143
+ - **Compute Region:** [More Information Needed]
144
+ - **Carbon Emitted:** [More Information Needed]
145
+
146
+ ## Technical Specifications [optional]
147
+
148
+ ### Model Architecture and Objective
149
+
150
+ [More Information Needed]
151
+
152
+ ### Compute Infrastructure
153
+
154
+ [More Information Needed]
155
+
156
+ #### Hardware
157
+
158
+ [More Information Needed]
159
+
160
+ #### Software
161
+
162
+ [More Information Needed]
163
+
164
+ ## Citation [optional]
165
+
166
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
167
+
168
+ **BibTeX:**
169
+
170
+ [More Information Needed]
171
+
172
+ **APA:**
173
+
174
+ [More Information Needed]
175
+
176
+ ## Glossary [optional]
177
+
178
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
179
+
180
+ [More Information Needed]
181
+
182
+ ## More Information [optional]
183
+
184
+ [More Information Needed]
185
+
186
+ ## Model Card Authors [optional]
187
+
188
+ [More Information Needed]
189
+
190
+ ## Model Card Contact
191
+
192
+ [More Information Needed]
193
+
194
+