Repository-Level Prompt Generation for Large Language Models of Code — mentioned by wsxiaoys

Wed, 29 Mar 2023 00:49:01 GMT

That‘ll be super interesting! Local context is definitely the key factor for small models achieving better quality than copilot (related: [1], [2]) . One things I’d really wanna have in Sourcegraph: A Search API supports custom retrieval / ranking. Research works (e.g [2]) show simple BoW fetched context is more efficient for code completion tasks. Disclaimer: I’m building https://github.com/TabbyML/tabby an open source alternative of copilot. [1]: https://arxiv.org/abs/2206.12839 [2]: https://arxiv.org/abs/2303.12570

Paper and discussion history. A mention is not an endorsement.

Repository-Level Prompt Generation for Large Language Models of Code · HackerPapers discussions

Repository-Level Prompt Generation for Large Language Models of Code — mentioned by wsxiaoys