aalkaswan commited on
Commit
20b6b4b
1 Parent(s): 3f7ecab

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - AISE-TUDelft/Capybara
5
+ tags:
6
+ - code
7
+ ---
8
+
9
+ # BinT5
10
+
11
+ - **Repository: https://github.com/AISE-TUDelft/Capybara-BinT5**
12
+ - **Paper: https://huggingface.co/papers/2301.01701**
13
+ - **Point of Contact: https://huggingface.co/aalkaswan**
14
+ - **Raw Data: https://zenodo.org/records/7229913**
15
+
16
+ BinT5 is a Binary Code Summarization model, the base models are [CodeT5]() and fine-tuned with [Capybara]().
17
+
18
+ We offer 5 variations of the model:
19
+
20
+ | Name | Training Data |
21
+ |-----------------------------------------------------|------------------------------------------------------|
22
+ | [BinT5-C](https://huggingface.co/AISE-TUDelft/BinT5-C) | C Source |
23
+ | [BinT5-Decom](https://huggingface.co/AISE-TUDelft/BinT5-Decom) | Decompiled C Binaries |
24
+ | [BinT5-Stripped](https://huggingface.co/AISE-TUDelft/BinT5-Stripped) | Stripped Decompiled C Binaries |
25
+ | [BinT5-Demi](https://huggingface.co/AISE-TUDelft/BinT5-Demi) | Demi-stripped Decompiled C Binaries |
26
+ | [BinT5-NoFunName](https://huggingface.co/AISE-TUDelft/BinT5-NoFunName) | Decompiled C Binaries with the Function Name removed |
27
+
28
+ ### Citation Information
29
+
30
+ ```
31
+ @inproceedings{alkaswan2023extending,
32
+ title={Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries},
33
+ author={Al-Kaswan, Ali and Ahmed, Toufique and Izadi, Maliheh and Sawant, Anand Ashok and Devanbu, Premkumar and van Deursen, Arie},
34
+ booktitle={2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)},
35
+ pages={260--271},
36
+ year={2023},
37
+ organization={IEEE}
38
+ }
39
+ ```