add readme

README.md

@@ -1,3 +1,59 @@
----
-license: mit
----
+# Codet5+ 220m Py Sum
+
+This Model is based on the [CodeT5+ (220m)](https://huggingface.co/Salesforce/codet5p-220m) from salesforce and was finetuned for the code summarization task by using the [XCodeGlue](https://github.com/microsoft/CodeXGLUE) Dataset. The Code is accessible on [Github](https://github.com/Paul-B98/mdl-ii).
+
+## Results
+
+| Modell | BLEU |
+| ------ | ---- | 
+| CodeT5-base-sum-python[^1] | 23.564 | 
+| CodeT5-base-multi-sum[^2]  | 23.985 | 
+| Code-Trans-S-ST[^3]        |  5.495 | 
+| Code-Trans-S-TF[^4]        | 21.093 | 
+| Code-Trans-S-MT[^5]        |  5.450 |  
+| Code-Trans-S-MT-TF[^6]     | 16.378 |  
+| Code-Trans-B-ST[^7]        |  4.638 | 
+| Code-Trans-B-TF[^8]        | 21.671 |
+| Code-Trans-B-MT[^9]        |  2.957 | 
+| Code-Trans-B-MT-TF[^10]     | 13.766 | 
+| Code-Trans-L-TF[^11]        | 23.306 | 
+| Code-Trans-L-MT[^12]        | 13.487 | 
+| Code-Trans-L-MT-TF[^13]     | 16.362 | 
+| **CodeT5+ 220m Py Sum***| 25.245 | 
+
+## Example on how to use
+
+The model can be easily download from Huggingface and used in a summarization pipeline.
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
+
+pipeline = SummarizationPipeline(
+    model=AutoModelWithLMHead.from_pretrained("Paul-B98/codet5p_220m_py_sum"),
+    tokenizer=AutoTokenizer.from_pretrained("Salesforce/codet5p-220m"),
+    device=0
+)
+
+example_method = """
+def greet(name):
+    print(f"Hello, {name}!")
+"""
+
+pipeline([example_method])[0]["summary_text"]
+```
+
+## References
+
+[^1]: https://huggingface.co/Salesforce/codet5-base-codexglue-sum-python
+[^2]: https://huggingface.co/Salesforce/codet5-base-multi-sum
+[^3]: https://huggingface.co/SEBIS/code_trans_t5_small_code_documentation_generation_python
+[^4]: https://huggingface.co/SEBIS/code_trans_t5_small_code_documentation_generation_python_transfer_learning_finetune
+[^5]: https://huggingface.co/SEBIS/code_trans_t5_small_code_documentation_generation_python_multitask
+[^6]: https://huggingface.co/SEBIS/code_trans_t5_small_code_documentation_generation_python_multitask_finetune
+[^7]: https://huggingface.co/SEBIS/code_trans_t5_base_code_documentation_generation_python
+[^8]: https://huggingface.co/SEBIS/code_trans_t5_base_code_documentation_generation_python_transfer_learning_finetune
+[^9]: https://huggingface.co/SEBIS/code_trans_t5_base_code_documentation_generation_python_multitask
+[^10]: https://huggingface.co/SEBIS/code_trans_t5_base_code_documentation_generation_python_multitask_finetune
+[^11]: https://huggingface.co/SEBIS/code_trans_t5_large_code_documentation_generation_python_transfer_learning_finetune
+[^12]: https://huggingface.co/SEBIS/code_trans_t5_large_code_documentation_generation_python_multitask
+[^13]: https://huggingface.co/SEBIS/code_trans_t5_large_code_documentation_generation_python_multitask_finetune