The Perl and Raku Conference 2024 in Las Vegas

PerlGPT is a large language model (LLM) comparable to ChatGPT 4.0, and trained on additional Perl-related content only. PerlGPT will be based on Meta's Code Llama (from Llama v2 or newer) language models, with all new components implemented in Perl where possible and released as free-and-open-source software (FOSS), unlike ChatGPT and other proprietary LLM systems.

Code Llama: Open Foundation Models for Code

Code Llama's documentation currently lists the following primarily-supported languages: "P****n, C++, Java, PHP, TypeScript, C#, and Bash". One of the outcomes of the PerlGPT project will be to effectively add Perl to this list. (PerlGPT may ultimately be released under an alternative name, such as "Perllama".)

Phase 1 consists of training a 13B input language model using Perl-related stimulus/response pairs curated from CPAN, and potentially other public Perl-specific data sources. The goal of phase 1 will be to deliver an LLM capable of generating pure-Perl source code in collaboration with a Perl programmer, similar to Microsoft Bing and GitHub Copilot. We will demonstrate our most up-to-date version of PerlGPT during the live conference.