The latest pre-trained model designed for high-quality code understanding and semantic retrieval, supporting long sequence processing of 8 programming languages.

Natural Language ProcessingSentence-transformersMultiple Languages

A multilingual code search model optimized based on the ModernBERT architecture, supporting semantic matching between natural language and code

Natural Language ProcessingRustMultiple Languages

A sentence transformer model specifically designed for code search, based on the ModernBERT architecture, supporting 8192 token long sequence processing

Natural Language ProcessingSafetensorsEnglish

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

Natural Language ProcessingSafetensorsEnglish

CodeBERTaPy is a RoBERTa-like model trained on GitHub's CodeSearchNet dataset specifically for Python language, designed for code optimization.

Natural Language ProcessingJaxOther

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

Natural Language ProcessingJax