wei commited on
Commit
e04d564
1 Parent(s): 93f79e5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md CHANGED
@@ -5,3 +5,73 @@ widget:
5
  - text: "function isStandardBrowserEnv ( ) { if ( typeof navigator !== 'undefined' && ( navigator . product === 'ReactNative' || navigator . product === 'NativeScript' || navigator . product === 'NS' ) ) { return false ; } return ( typeof window !== 'undefined' && typeof document !== 'undefined' ) ; }"
6
 
7
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  - text: "function isStandardBrowserEnv ( ) { if ( typeof navigator !== 'undefined' && ( navigator . product === 'ReactNative' || navigator . product === 'NativeScript' || navigator . product === 'NS' ) ) { return false ; } return ( typeof window !== 'undefined' && typeof document !== 'undefined' ) ; }"
6
 
7
  ---
8
+
9
+
10
+
11
+ # CodeTrans model for code documentation generation javascript
12
+ Pretrained model on programming language javascript using the t5 base model architecture. It was first released in
13
+ [this repository](https://github.com/agemagician/CodeTrans). This model is trained on tokenized javascript code functions: it works best with tokenized javascript functions.
14
+
15
+
16
+ ## Model description
17
+
18
+ This CodeTrans model is based on the `t5-base` model. It has its own SentencePiece vocabulary model. It used multi-task training on 13 supervised tasks in the software development domain and 7 unsupervised datasets.
19
+
20
+ ## Intended uses & limitations
21
+
22
+ The model could be used to generate the description for the javascript function or be fine-tuned on other javascript code tasks. It can be used on unparsed and untokenized javascript code. However, if the javascript code is tokenized, the performance should be better.
23
+
24
+ ### How to use
25
+
26
+ Here is how to use this model to generate javascript function documentation using Transformers SummarizationPipeline:
27
+
28
+ ```python
29
+ from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
30
+
31
+ pipeline = SummarizationPipeline(
32
+ model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_base_code_documentation_generation_javascript_multitask"),
33
+ tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_base_code_documentation_generation_javascript_multitask", skip_special_tokens=True),
34
+ device=0
35
+ )
36
+
37
+ tokenized_code = "function isStandardBrowserEnv ( ) { if ( typeof navigator !== 'undefined' && ( navigator . product === 'ReactNative' || navigator . product === 'NativeScript' || navigator . product === 'NS' ) ) { return false ; } return ( typeof window !== 'undefined' && typeof document !== 'undefined' ) ; }"
38
+ pipeline([tokenized_code])
39
+ ```
40
+ Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/multitask/pre-training/function%20documentation%20generation/javascript/base_model.ipynb).
41
+ ## Training data
42
+
43
+ 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)
44
+
45
+ ## Training procedure
46
+
47
+ ### Multi-task Pretraining
48
+
49
+ The model was trained on a single TPU Pod V3-8 for 440,000 steps in total, using sequence length 512 (batch size 4096).
50
+ It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture.
51
+ The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
52
+
53
+
54
+ ## Evaluation results
55
+
56
+ For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):
57
+
58
+ Test results :
59
+
60
+ | Language / Model | Python | Java | Go | Php | Ruby | JavaScript |
61
+ | -------------------- | :------------: | :------------: | :------------: | :------------: | :------------: | :------------: |
62
+ | CodeTrans-ST-Small | 17.31 | 16.65 | 16.89 | 23.05 | 9.19 | 13.7 |
63
+ | CodeTrans-ST-Base | 16.86 | 17.17 | 17.16 | 22.98 | 8.23 | 13.17 |
64
+ | CodeTrans-TF-Small | 19.93 | 19.48 | 18.88 | 25.35 | 13.15 | 17.23 |
65
+ | CodeTrans-TF-Base | 20.26 | 20.19 | 19.50 | 25.84 | 14.07 | 18.25 |
66
+ | CodeTrans-TF-Large | 20.35 | 20.06 | **19.54** | 26.18 | 14.94 | **18.98** |
67
+ | CodeTrans-MT-Small | 19.64 | 19.00 | 19.15 | 24.68 | 14.91 | 15.26 |
68
+ | CodeTrans-MT-Base | **20.39** | 21.22 | 19.43 | **26.23** | **15.26** | 16.11 |
69
+ | CodeTrans-MT-Large | 20.18 | **21.87** | 19.38 | 26.08 | 15.00 | 16.23 |
70
+ | CodeTrans-MT-TF-Small | 19.77 | 20.04 | 19.36 | 25.55 | 13.70 | 17.24 |
71
+ | CodeTrans-MT-TF-Base | 19.77 | 21.12 | 18.86 | 25.79 | 14.24 | 18.62 |
72
+ | CodeTrans-MT-TF-Large | 18.94 | 21.42 | 18.77 | 26.20 | 14.19 | 18.83 |
73
+ | State of the art | 19.06 | 17.65 | 18.07 | 25.16 | 12.16 | 14.90 |
74
+
75
+
76
+ > 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/)
77
+