Efficient Code Embeddings from Code Generation Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kryvosheieva, Daria, Sturua, Saba, Günther, Michael, Martens, Scott, Xiao, Han
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912558812758016
author Kryvosheieva, Daria
Sturua, Saba
Günther, Michael
Martens, Scott
Xiao, Han
author_facet Kryvosheieva, Daria
Sturua, Saba
Günther, Michael
Martens, Scott
Xiao, Han
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21290
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Code Embeddings from Code Generation Models
Kryvosheieva, Daria
Sturua, Saba
Günther, Michael
Martens, Scott
Xiao, Han
Computation and Language
Artificial Intelligence
Information Retrieval
68T50
I.2.7
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.
title Efficient Code Embeddings from Code Generation Models
topic Computation and Language
Artificial Intelligence
Information Retrieval
68T50
I.2.7
url https://arxiv.org/abs/2508.21290