AhmedSSoliman
commited on
Commit
·
c249ba4
1
Parent(s):
bdf9146
Update README.md
Browse files
README.md
CHANGED
@@ -7,13 +7,6 @@ widget:
|
|
7 |
- text: 'find all files in directory "/mydir" with extension ".txt"'
|
8 |
---
|
9 |
|
10 |
-
---
|
11 |
-
Tasks:
|
12 |
-
- Translation
|
13 |
-
- Code Generation
|
14 |
-
- Text2Text Generation
|
15 |
-
- Text Generation
|
16 |
-
---
|
17 |
# MarianCG: A TRANSFORMER MODEL FOR AUTOMATIC CODE GENERATION
|
18 |
This model is to improve the solving of the code generation problem and implement a transformer model that can work with high accurate results. We implemented MarianCG transformer model which is a code generation model that can be able to generate code from natural language. This work declares the impact of using Marian machine translation model for solving the problem of code generation. In our implementation we prove that a machine translation model can be operated and working as a code generation model.Finally, we set the new contributors and state-of-the-art on CoNaLa reaching a BLEU score of 30.92 in the code generation problem with CoNaLa dataset.
|
19 |
|
@@ -33,4 +26,13 @@ output = model.generate(**tokenizer(NL_input, padding="max_length", truncation=T
|
|
33 |
output_code = tokenizer.decode(output[0], skip_special_tokens=True)
|
34 |
```
|
35 |
|
36 |
-
This model is available in spaces at: https://huggingface.co/spaces/AhmedSSoliman/MarianCG_NL-to-Code
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
- text: 'find all files in directory "/mydir" with extension ".txt"'
|
8 |
---
|
9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
# MarianCG: A TRANSFORMER MODEL FOR AUTOMATIC CODE GENERATION
|
11 |
This model is to improve the solving of the code generation problem and implement a transformer model that can work with high accurate results. We implemented MarianCG transformer model which is a code generation model that can be able to generate code from natural language. This work declares the impact of using Marian machine translation model for solving the problem of code generation. In our implementation we prove that a machine translation model can be operated and working as a code generation model.Finally, we set the new contributors and state-of-the-art on CoNaLa reaching a BLEU score of 30.92 in the code generation problem with CoNaLa dataset.
|
12 |
|
|
|
26 |
output_code = tokenizer.decode(output[0], skip_special_tokens=True)
|
27 |
```
|
28 |
|
29 |
+
This model is available in spaces using gradio at: https://huggingface.co/spaces/AhmedSSoliman/MarianCG_NL-to-Code
|
30 |
+
|
31 |
+
|
32 |
+
---
|
33 |
+
Tasks:
|
34 |
+
- Translation
|
35 |
+
- Code Generation
|
36 |
+
- Text2Text Generation
|
37 |
+
- Text Generation
|
38 |
+
---
|