hanxiao
Abstract
Jina-code-embeddings uses an autoregressive backbone pre-trained on text and code to generate embeddings for code retrieval, question-answering, and similarity identification.
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.
Community
our new code embedding
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey (2025)
- Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning (2025)
- Causal2Vec: Improving Decoder-only LLMs as Versatile Embedding Models (2025)
- Diffusion is a code repair operator and generator (2025)
- Modeling Code: Is Text All You Need? (2025)
- Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking (2025)
- When Retriever Meets Generator: A Joint Model for Code Comment Generation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper