paper-with-me

홈 › Papers

Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing

2025-02-20 · Aviv Bick, Tobias Katsch, Nimit Sohoni, Arjun Desai, Albert Gu

We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle significantly larger batch sizes than Transformer-based models while maintaining comparable benchmark performance. Furthermore, Llamba demonstrates the effectiveness of cross-architecture distillation using MOHAWK (Bick et al., 2024), achieving these results with less than 0.1% of the training data typically used for models of similar size. To take full advantage of their efficiency, we provide an optimized implementation of Llamba for resource-constrained devices such as smartphones and edge platforms, offering a practical and memory-efficient alternative to Transformers. Overall, Llamba improves the tradeoff between speed, memory efficiency, and performance, making high-quality language models more accessible.

📄 PDF Abstract BibTeX arXiv:2502.14458

Code (0)

등록된 구현이 없습니다.

Tasks

Mamba

Methods 이 논문이 사용한 방법론

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

Reverse Distillation: Consistently Scaling Protein Language Model Representations

2026-03-08 · Darius Catrina, Christian Bepler, Samuel Sledzieski, Rohit Singh arxiv

Unlike the predictable scaling laws in natural language processing and computer vision, protein language models (PLMs) scale poorly: for many tasks, models within the same family plateau or even decrease in performance, …

Protein Language Model

Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners

2025-02-27 · Daniele Paliotta, Junxiong Wang, Matteo Pagliardini, Kevin Y. Li 외

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Cha…

MambaMathematical Reasoning

Rethinking Data Distillation: Do Not Overlook Calibration

2023-07-24 · ICCV 2023 1 · Dongyao Zhu, Bowen Lei, Jie Zhang, Yanbo Fang 외

Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods. Existing calibration methods such as temperature scaling and mixup work well for networks train…

Dataset Distillation

Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling

2025-09-01 · Sachin Goyal, David Lopez-Paz, Kartik Ahuja arxiv

In the past year, distillation has seen a renewed prominence in large language model (LLM) pretraining, exemplified by the Llama-3.2 and Gemma model families. While distillation has historically been shown to improve sta…

Scaling Transformer to 1M tokens and beyond with RMT

2023-04-19 · Aydar Bulatov, Yuri Kuratov, Yermek Kapushev, Mikhail S. Burtsev

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-t…

Language ModelingLanguage ModellingNatural Language UnderstandingRetrieval