SEBIS/code_trans_t5_small_source_code_summarization_sql

1---2tags:3- summarization4widget:5- text: "select time ( col0 ) from tab0"6 7---8 9 10 11# CodeTrans model for source code summarization sql12Pretrained model on programming language sql using the t5 small model architecture. It was first released in13[this repository](https://github.com/agemagician/CodeTrans). This model is trained on tokenized sql code functions: it works best with tokenized sql functions.14 15 16## Model description17 18This CodeTrans model is based on the `t5-small` model. It has its own SentencePiece vocabulary model. It used single-task training on source code summarization sql dataset.19 20## Intended uses & limitations21 22The model could be used to generate the description for the sql function or be fine-tuned on other sql code tasks. It can be used on unparsed and untokenized sql code. However, if the sql code is tokenized, the performance should be better.23 24### How to use25 26Here is how to use this model to generate sql function documentation using Transformers SummarizationPipeline:27 28```python29from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline30 31pipeline = SummarizationPipeline(32    model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_small_source_code_summarization_sql"),33    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_small_source_code_summarization_sql", skip_special_tokens=True),34    device=035)36 37tokenized_code = "select time ( col0 ) from tab0"38pipeline([tokenized_code])39```40Run this example in [colab notebook](https://github.com/agemagician/CodeTrans/blob/main/prediction/single%20task/source%20code%20summarization/sql/small_model.ipynb).41## Training data42 43The 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 46## Evaluation results47 48For the source code summarization tasks, different models achieves the following results on different programming languages (in BLEU score):49 50Test results :51 52|   Language / Model   |     Python     |       SQL      |       C#       |53| -------------------- | :------------: | :------------: | :------------: |54|   CodeTrans-ST-Small    |      8.45      |     17.55      |     19.74      |55|   CodeTrans-ST-Base     |      9.12      |     15.00      |     18.65      | 56|   CodeTrans-TF-Small    |     10.06      |     17.71      |     20.40      |57|   CodeTrans-TF-Base     |     10.94      |     17.66      |     21.12      |58|   CodeTrans-TF-Large    |     12.41      |     18.40      |     21.43      |59|   CodeTrans-MT-Small    |     13.11      |     19.15      |     22.39      |60|   CodeTrans-MT-Base     |   **13.37**    |     19.24      |     23.20      |61|   CodeTrans-MT-Large    |     13.24      |     19.40      |   **23.57**    |62|   CodeTrans-MT-TF-Small |     12.10      |     18.25      |     22.03      |63|   CodeTrans-MT-TF-Base  |     10.64      |     16.91      |     21.40      |64|   CodeTrans-MT-TF-Large |     12.14      |   **19.98**    |     21.10      |65|   CODE-NN   |       --       |     18.40      |     20.50      |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