Efficient Code Embeddings from Code Generation Models

Daria Kryvosheieva, Saba Sturua, Michael Günther, Scott Martens, Han Xiao

Efficient Code Embeddings from Code Generation Models: 21 upvotes on Hugging Face Daily Papers, #7 of 19 papers on 2025-09-01. Day-by-day upvote history.

jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.