SEBIS/code_trans_t5_base_code_comment_generation_java

1---2tags:3- summarization4widget:5- text: "protected String renderUri ( URI uri ) { return uri . toASCIIString ( ) ; }"6 7---8 9 10# CodeTrans model for code comment generation java11Pretrained model on programming language java using the t5 base model architecture. It was first released in12[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 description16 17This 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 & limitations20 21The 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 use24 25Here is how to use this model to generate java function documentation using Transformers SummarizationPipeline:26 27```python28from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline29 30pipeline = 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=034)35 36tokenized_code = "protected String renderUri ( URI uri ) { return uri . toASCIIString ( ) ; }"37pipeline([tokenized_code])38```39Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/single%20task/code%20comment%20generation/base_model.ipynb).40## Training data41 42The 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 results46 47For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):48 49Test 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 70