Optimizing Large Language Models for OpenAPI Code Completion — HN submission

Tue, 18 Jun 2024 08:15:46 GMT

Show HN: I reproduced Code Llama fill-in-the-middle code completion training

As part of my master's thesis on optimizing LLMs for code completion in OpenAPI format, I implemented a script for fine-tuning Code Llama for Copilot-style code completion. Surprisingly, I was not able to find a similar implementation before since most works focus on instruction fine-tuning for chat-like interaction. Related publication: https://arxiv.org/abs/2405.15729 Code Llama fill-in-the-middle fine-tuning: https://github.com/BohdanPetryshyn/code-llama-fim-fine-tunin... OpenAPI completion benchmark: https://github.com/BohdanPetryshyn/openapi-completion-benchm...

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Optimizing Large Language Models for OpenAPI Code Completion · HackerPapers discussions

Optimizing Large Language Models for OpenAPI Code Completion — HN submission