The Mamba in the Llama: Distilling and Accelerating Hybrid Models

• URL: http://arxiv.org/abs/2408.15237v1
• Date: Tue, 27 Aug 2024 17:56:11 GMT
• Title: The Mamba in the Llama: Distilling and Accelerating Hybrid Models
• Authors: Junxiong Wang, Daniele Paliotta, Avner May, Alexander M. Rush, Tri Dao,
• Abstract summary: We show that it is feasible to distill large Transformers into linear RNNs by reusing the linear projection weights from attention layers with academic GPU resources. The resulting hybrid model, which incorporates a quarter of the attention layers, achieves performance comparable to the original Transformer in chat benchmarks.
• Score: 76.64055251296548
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the challenge of converting these pretrained models for deployment. We demonstrate that it is feasible to distill large Transformers into linear RNNs by reusing the linear projection weights from attention layers with academic GPU resources. The resulting hybrid model, which incorporates a quarter of the attention layers, achieves performance comparable to the original Transformer in chat benchmarks and outperforms open-source hybrid Mamba models trained from scratch with trillions of tokens in both chat benchmarks and general benchmarks. Moreover, we introduce a hardware-aware speculative decoding algorithm that accelerates the inference speed of Mamba and hybrid models. Overall we show how, with limited computation resources, we can remove many of the original attention layers and generate from the resulting model more efficiently. Our top-performing model, distilled from Llama3-8B-Instruct, achieves a 29.61 length-controlled win rate on AlpacaEval 2 against GPT-4 and 7.35 on MT-Bench, surpassing the best instruction-tuned linear RNN model.

Related papers

• Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation [36.44678935063189]
  mmMamba is a framework for developing linear-complexity native multimodal state space models. Our approach enables the direct conversion of trained decoder-only MLLMs to linear-complexity architectures.
  arXiv  Detail & Related papers  (2025-02-18T18:59:57Z)
• Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models [92.36510016591782]
  We present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs) Our method, called MOHAWK, is able to distill a Mamba-2 variant based on the Phi-1.5 architecture using only 3B tokens and a hybrid version (Hybrid Phi-Mamba) using 5B tokens. Despite using less than 1% of the training data typically used to train models from scratch, Phi-Mamba boasts substantially stronger performance compared to all past open-source non-Transformer models.
  arXiv  Detail & Related papers  (2024-08-19T17:48:11Z)
• How Effective are State Space Models for Machine Translation? [19.509486069758495]
  Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers. It remains unclear whether these models are competitive with transformers in machine translation.
  arXiv  Detail & Related papers  (2024-07-07T20:21:49Z)
• An Empirical Study of Mamba-based Language Models [69.74383762508805]
  Selective state-space models (SSMs) like Mamba overcome some shortcomings of Transformers. We present a direct comparison between 8B-context Mamba, Mamba-2, and Transformer models trained on the same datasets. We find that the 8B Mamba-2-Hybrid exceeds the 8B Transformer on all 12 standard tasks.
  arXiv  Detail & Related papers  (2024-06-12T05:25:15Z)
• Parallelizing Linear Transformers with the Delta Rule over Sequence Length [49.88826673324244]
  This work describes a hardware-efficient algorithm for training linear transformers with the delta rule. We train a 1.3B model for 100B tokens and find that it outperforms recent linear-time baselines.
  arXiv  Detail & Related papers  (2024-06-10T17:24:42Z)
• Demystify Mamba in Vision: A Linear Attention Perspective [72.93213667713493]
  Mamba is an effective state space model with linear computation complexity. We show that Mamba shares surprising similarities with linear attention Transformer. We propose a Mamba-Inspired Linear Attention (MILA) model by incorporating the merits of these two key designs into linear attention.
  arXiv  Detail & Related papers  (2024-05-26T15:31:09Z)
• Is Mamba Effective for Time Series Forecasting? [30.85990093479062]
  We propose a Mamba-based model named Simple-Mamba (S-Mamba) for time series forecasting. Specifically, we tokenize the time points of each variate autonomously via a linear layer. Experiments on thirteen public datasets prove that S-Mamba maintains low computational overhead and achieves leading performance.
  arXiv  Detail & Related papers  (2024-03-17T08:50:44Z)
• Is Mamba Capable of In-Context Learning? [63.682741783013306]
  State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL) This work provides empirical evidence that Mamba, a newly proposed state space model, has similar ICL capabilities.
  arXiv  Detail & Related papers  (2024-02-05T16:39:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.