Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Chen, Song, Yin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.08651
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912373792571392
author Wu, Chen
Song, Yin
author_facet Wu, Chen
Song, Yin
contents We present MegaBeam-Mistral-7B, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification. Evaluated on three long-context benchmarks, our 7B-parameter model demonstrates superior in-context learning performance on HELMET and robust retrieval and tracing capability on RULER. It is currently the only open model to achieve competitive long-range reasoning on BABILong at 512K context length without RAG or targeted fine-tuning. Released as fully open source under the Apache 2.0 license, the model has been downloaded over 100,000 times on Hugging Face. Model available at: https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k
format Preprint
id arxiv_https___arxiv_org_abs_2505_08651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
Wu, Chen
Song, Yin
Computation and Language
Machine Learning
We present MegaBeam-Mistral-7B, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification. Evaluated on three long-context benchmarks, our 7B-parameter model demonstrates superior in-context learning performance on HELMET and robust retrieval and tracing capability on RULER. It is currently the only open model to achieve competitive long-range reasoning on BABILong at 512K context length without RAG or targeted fine-tuning. Released as fully open source under the Apache 2.0 license, the model has been downloaded over 100,000 times on Hugging Face. Model available at: https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k
title Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.08651