Update README.md
Browse files
README.md
CHANGED
@@ -5,3 +5,65 @@ widget:
|
|
5 |
- text: "protected String renderUri ( URI uri ) { return uri . toASCIIString ( ) ; }"
|
6 |
|
7 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
- text: "protected String renderUri ( URI uri ) { return uri . toASCIIString ( ) ; }"
|
6 |
|
7 |
---
|
8 |
+
|
9 |
+
|
10 |
+
# CodeTrans model for code documentation generation java
|
11 |
+
Pretrained model on programming language java using the t5 base model architecture. It was first released in
|
12 |
+
[this repository](https://github.com/agemagician/CodeTrans). This model is trained on tokenized java code functions: it works best with tokenized java functions.
|
13 |
+
|
14 |
+
|
15 |
+
## Model description
|
16 |
+
|
17 |
+
This CodeTrans model is based on the `t5-base` model. It has its own SentencePiece vocabulary model. It used single-task training on Code Comment Generation dataset.
|
18 |
+
|
19 |
+
## Intended uses & limitations
|
20 |
+
|
21 |
+
The model could be used to generate the description for the java function or be fine-tuned on other java code tasks. It can be used on unparsed and untokenized java code. However, if the java code is tokenized, the performance should be better.
|
22 |
+
|
23 |
+
### How to use
|
24 |
+
|
25 |
+
Here is how to use this model to generate java function documentation using Transformers SummarizationPipeline:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
|
29 |
+
|
30 |
+
pipeline = SummarizationPipeline(
|
31 |
+
model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_base_code_comment_generation_java"),
|
32 |
+
tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_base_code_comment_generation_java", skip_special_tokens=True),
|
33 |
+
device=0
|
34 |
+
)
|
35 |
+
|
36 |
+
tokenized_code = "protected String renderUri ( URI uri ) { return uri . toASCIIString ( ) ; }"
|
37 |
+
pipeline([tokenized_code])
|
38 |
+
```
|
39 |
+
Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/single%20task/code%20comment%20generation/base_model.ipynb).
|
40 |
+
## Training data
|
41 |
+
|
42 |
+
The supervised training tasks datasets can be downloaded on [Link](https://www.dropbox.com/sh/488bq2of10r4wvw/AACs5CGIQuwtsD7j_Ls_JAORa/finetuning_dataset?dl=0&subfolder_nav_tracking=1)
|
43 |
+
|
44 |
+
|
45 |
+
## Evaluation results
|
46 |
+
|
47 |
+
For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):
|
48 |
+
|
49 |
+
Test results :
|
50 |
+
|
51 |
+
| Language / Model | Java |
|
52 |
+
| -------------------- | :------------: |
|
53 |
+
| CodeTrans-ST-Small | 37.98 |
|
54 |
+
| CodeTrans-ST-Base | 38.07 |
|
55 |
+
| CodeTrans-TF-Small | 38.56 |
|
56 |
+
| CodeTrans-TF-Base | 39.06 |
|
57 |
+
| CodeTrans-TF-Large | **39.50** |
|
58 |
+
| CodeTrans-MT-Small | 20.15 |
|
59 |
+
| CodeTrans-MT-Base | 27.44 |
|
60 |
+
| CodeTrans-MT-Large | 34.69 |
|
61 |
+
| CodeTrans-MT-TF-Small | 38.37 |
|
62 |
+
| CodeTrans-MT-TF-Base | 38.90 |
|
63 |
+
| CodeTrans-MT-TF-Large | 39.25 |
|
64 |
+
| State of the art | 38.17 |
|
65 |
+
|
66 |
+
|
67 |
+
|
68 |
+
> Created by [Ahmed Elnaggar](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/) and Wei Ding | [LinkedIn](https://www.linkedin.com/in/wei-ding-92561270/)
|
69 |
+
|