Code clustering

[shaileshj2803]

Can i use the DOBF model for code clustering to find similar code patterns? If so can you guide which model to begin with or if you have any examples?

[brozi]

Hi. You can use our released DOBF models to do that (those models are using the roberta tokenizer and architecture). You can start with the DOBF + DAE version for instance. I would expect it to give similar representations to code with similar semantics (since they would be likely to have similar variable names). https://github.com/facebookresearch/CodeGen/blob/main/docs/dobf.md#release