Saved in:
Bibliographic Details
Main Authors: Pavlichenko, Nikita, Nazarov, Iurii, Dolgov, Ivan, Garanina, Ekaterina, Ustalov, Dmitry, Bondyrev, Ivan, Lysaniuk, Kseniia, Vu, Evgeniia, Chekmenev, Kirill, Shtok, Joseph, Golubev, Yaroslav, Semenkin, Anton, Sazanovich, Uladzislau
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.05788
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914079129468928
author Pavlichenko, Nikita
Nazarov, Iurii
Dolgov, Ivan
Garanina, Ekaterina
Ustalov, Dmitry
Bondyrev, Ivan
Lysaniuk, Kseniia
Vu, Evgeniia
Chekmenev, Kirill
Shtok, Joseph
Golubev, Yaroslav
Semenkin, Anton
Sazanovich, Uladzislau
author_facet Pavlichenko, Nikita
Nazarov, Iurii
Dolgov, Ivan
Garanina, Ekaterina
Ustalov, Dmitry
Bondyrev, Ivan
Lysaniuk, Kseniia
Vu, Evgeniia
Chekmenev, Kirill
Shtok, Joseph
Golubev, Yaroslav
Semenkin, Anton
Sazanovich, Uladzislau
contents We present the Mellum models family, open-weight code completion models designed for interactive use in JetBrains IDEs. Mellums have 4B parameters, adopt a Llama-style architecture, and are pre-trained on ~4T tokens of permissively licensed, multi-language code. Our studies show that (i) careful data curation and staged training significantly improve the model's quality, (ii) editor-critical capabilities such as context packing are necessary for high-quality suggestions, and (iii) a compact, task-focused model can meet the cost and latency constraints of interactive completion. In the paper, we describe an end-to-end industrial pipeline for producing contextualized in-editor completion: disciplined data governance, multi-stage training that includes fill-in-the-middle and project context via supervised fine-tuning, and alignment via direct preference optimization using feedback from real-world scenarios. Our quality evaluations include both large-scale offline benchmarks and online telemetry from production deployments in JetBrains IDEs. Mellums are released under the Apache-2.0 license on HuggingFace, with a public model card providing a reproducible reference for practitioners. Our experience offers a pragmatic blueprint for taking a focused, open model from a research prototype to at scale production for hundreds of thousands of users.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding
Pavlichenko, Nikita
Nazarov, Iurii
Dolgov, Ivan
Garanina, Ekaterina
Ustalov, Dmitry
Bondyrev, Ivan
Lysaniuk, Kseniia
Vu, Evgeniia
Chekmenev, Kirill
Shtok, Joseph
Golubev, Yaroslav
Semenkin, Anton
Sazanovich, Uladzislau
Software Engineering
Artificial Intelligence
Machine Learning
We present the Mellum models family, open-weight code completion models designed for interactive use in JetBrains IDEs. Mellums have 4B parameters, adopt a Llama-style architecture, and are pre-trained on ~4T tokens of permissively licensed, multi-language code. Our studies show that (i) careful data curation and staged training significantly improve the model's quality, (ii) editor-critical capabilities such as context packing are necessary for high-quality suggestions, and (iii) a compact, task-focused model can meet the cost and latency constraints of interactive completion. In the paper, we describe an end-to-end industrial pipeline for producing contextualized in-editor completion: disciplined data governance, multi-stage training that includes fill-in-the-middle and project context via supervised fine-tuning, and alignment via direct preference optimization using feedback from real-world scenarios. Our quality evaluations include both large-scale offline benchmarks and online telemetry from production deployments in JetBrains IDEs. Mellums are released under the Apache-2.0 license on HuggingFace, with a public model card providing a reproducible reference for practitioners. Our experience offers a pragmatic blueprint for taking a focused, open model from a research prototype to at scale production for hundreds of thousands of users.
title Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding
topic Software Engineering
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.05788