CodeTrans
CodeTrans copied to clipboard
Pretrained Language Models for Source code
Rather than just using the pre-trained model for single task Source Code Summarization. Will it better to integrate a latest LLM in it?
For example let's teach it langchain with carefully annotated question answer pairs dataset. Thanks in advance.
I'm trying to fine-tune the model on the Kotlin dataset for code comment/code documentation tasks. But I getting RuntimeError: Could not infer dtype of dict. more details are available in...