Papers
arxiv:2510.13697

On Pretraining for Project-Level Code Completion

Published on Oct 15
· Submitted by Evgeniy Glukhov on Oct 17
Authors:
,

Abstract

Extending the context window and adapting to a new rotary positional embedding scaling parameter improve repository-level code completion in OpenCoder, achieving performance comparable to larger models with less data.

AI-generated summary

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how different repository-processing strategies affect in-context learning in OpenCoder, a 1.5B-parameter model. We extend its context window from 4,096 to 16,384 tokens by training on additional 1B tokens of curated repository-level data. Despite relying on a smaller dataset than competing models (which often use hundreds of billions of tokens), our model achieves comparable performance on the Long Code Arena benchmark. We find that various repository-processing techniques yield similarly strong results, with the primary gain coming from adapting to a new rotary positional embedding (RoPE) scaling parameter. Finally, we show that a simpler file-level training approach at the original sequence length remains highly effective, opening up repository-level code completion research to settings with more constrained data and compute resources.

Community

Paper submitter
edited 1 day ago

We provide all the checkpoints here.

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

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

Sign up or log in to comment

Models citing this paper 32

Browse 32 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.13697 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.13697 in a Space README.md to link it from this page.

Collections including this paper 1