# Code search optimization

CodeModernBERT-Owl-3.0 is the final pre-trained version of the multilingual long context encoder model in the CodeModernBERT series, optimized for downstream code-related tasks such as code search, code summarization, error repair, and representation learning.

A sentence transformer model specifically designed for code search, based on ModernBERT architecture, supporting sequence lengths of up to 2048 tokens

A Python code auto-completion model fine-tuned on GPT-Neo-125M, specializing in method completion tasks

This is a RoBERTa model pre-trained on the CodeSearchNet dataset, specifically designed for Golang masked language modeling tasks.

A pre-trained Java code documentation generation model based on T5 small architecture, specifically designed to generate descriptive documentation for Java functions