REVIEW 35 cited by
Zamba: A Compact 7B SSM Hybrid Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Zamba: A Compact 7B SSM Hybrid Model
read the original abstract
In this technical report, we present Zamba, a novel 7B SSM-transformer hybrid model which achieves competitive performance against leading open-weight models at a comparable scale. Zamba is trained on 1T tokens from openly available datasets and is the best non-transformer model at this scale. Zamba pioneers a unique architecture combining a Mamba backbone with a single shared attention module, thus obtaining the benefits of attention at minimal parameter cost. Due to its architecture, Zamba is significantly faster at inference than comparable transformer models and requires substantially less memory for generation of long sequences. Zamba is pretrained in two phases: the first phase is based on existing web datasets, while the second one consists of annealing the model over high-quality instruct and synthetic datasets, and is characterized by a rapid learning rate decay. We open-source the weights and all checkpoints for Zamba, through both phase 1 and annealing phases.
Forward citations
Cited by 35 Pith papers
-
Morphing into Hybrid Attention Models
FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient...
-
Forget Attention: Importance-Aware Attention Is All You Need
SISA adds an SSM importance term inside the attention score and runs the full operation as one SDPA call on augmented Q/K vectors, reporting better LAMBADA and perfect NIAH at small scale.
-
Mixture of Layers with Hybrid Attention
Mixture of Layers replaces monolithic transformer blocks with routed thin parallel blocks using hybrid attention that combines a shared softmax block for global context with Gated DeltaNet linear attention in the rout...
-
Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control
Star Elastic trains N nested submodels in a single post-training job on a parent reasoning LLM, supporting elastic budget control that matches or exceeds independent baselines while cutting training compute by up to 360x.
-
Hidden State Poisoning Attacks against Mamba-based Language Models
Short input phrases can irreversibly overwrite hidden states in Mamba models, impairing information retrieval on a new benchmark while leaving pure Transformer models unaffected.
-
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Transformers and SSMs are unified through structured state space duality, producing a 2-8X faster Mamba-2 model that remains competitive with Transformers.
-
DSSMs: State Space Models with Explicit Memory via Delay Differential Equations
Delay State Space Models augment diagonal SSMs with explicit delayed feedback, stable discrete parameterization, and FFT training, improving delayed-retrieval tasks and matching or beating S4D on most standard sequenc...
-
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
DART augments Mamba-2 with attention over its own chunk state contributions, improving associative recall and retrieval with a smaller inference cache than token-level attention.
-
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale
Capability, unlike representation, converges to access-complete hybrid architectures, and a witness task separates pure from hybrid families under fixed budgets.
-
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale
Long-context capability converges to hybrid architectures pairing O(1) state with a scalable index; pure scaling of SSMs or Transformers alone hits information, horizon, or circuit walls.
-
Zamba2-VL Technical Report
Zamba2-VL is a family of 1.2B–7B hybrid Mamba2-transformer vision-language models that match leading transformer VLMs on image, reasoning, OCR, grounding and counting benchmarks while delivering roughly 10x lower time...
-
The Routing and Filtering Structure of Attention
Attention decomposes into low-rank routing and symmetric filtering; disentangled S-D attention reveals a spectral cascade allowing early-layer linearization at under 5% perplexity cost.
-
Priming: Hybrid State Space Models From Pre-trained Transformers
Priming transfers knowledge from pre-trained Transformers to hybrid SSM-attention models, recovering performance with minimal additional tokens and showing Gated KalmaNet outperforming Mamba-2 on long-context reasonin...
-
ZAYA1-8B Technical Report
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
-
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
-
HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models
HubRouter is a sub-quadratic routing primitive using learned hubs that replaces attention layers in hybrid models while delivering competitive perplexity and large throughput gains.
-
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
PoM is a new linear-complexity token mixer using learned polynomials that matches attention performance in transformers while enabling efficient long-sequence processing.
-
When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models
AMOR uses output entropy to gate attention in recurrent hybrids, matching full attention performance at roughly 22% attention invocations across 180M-1.5B models.
-
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
Gated KalmaNet uses exact Kalman gain computation with adaptive gating and Chebyshev iteration to improve SSM performance on long-context tasks over prior approximations like DeltaNet.
-
Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs
STAGE synthesizes high-fidelity Chakra-format execution graphs for distributed LLM workloads from symbolic tensor definitions, validated against real 128-GPU H100 traces and scaled to 32K GPUs.
-
SpikingBrain: Spiking Brain-inspired Large Models
SpikingBrain-7B and SpikingBrain-76B achieve Transformer-comparable performance after continual pre-training on 150B tokens, with over 100x TTFT speedup on 4M-token sequences and 69.15% sparsity from event-driven spiking.
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
MiniMax-M1 is a 456B parameter hybrid-attention MoE model trained with CISPO RL that achieves performance comparable or superior to DeepSeek-R1 and Qwen3-235B on reasoning and software engineering tasks while training...
-
DataComp-LM: In search of the next generation of training sets for language models
DCLM-Baseline dataset lets a 7B model reach 64% 5-shot MMLU accuracy after 2.6T tokens, beating prior open-data models by 6.6 points on MMLU with 40% less compute.
-
An Empirical Study of Mamba-based Language Models
An 8B Mamba-2-Hybrid with 43% Mamba-2, 7% attention, and 50% MLP layers exceeds an 8B Transformer by 2.65 points on average across 12 tasks and matches it on 23 long-context tasks while enabling up to 8x faster inference.
-
ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution
ZUNA1.1, an open-source 380M EEG diffusion autoencoder, reconstructs variable-length, flexibly masked EEG at least as well as its predecessor and far better than spherical spline interpolation.
-
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency
MOSAIC uses an Integer Linear Program scheduler for expert placement and prompt assignment plus adaptive aggregation to achieve 1.7-2.3x end-to-end speedup on 4-GPU MoA workloads while keeping accuracy within 0.1pp.
-
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models
KL divergence provides a superior forward-only metric for identifying quantization-sensitive parts in SSM-Transformer hybrids, outperforming MSE and SQNR and supporting practical mixed-precision deployment on edge devices.
-
The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency
Mamba-3 architectural changes made for hyperscale GPUs raise edge latency 28% at 880M parameters and 48% at 15M parameters relative to earlier Mamba designs.
-
Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction
Distill-then-Replace builds task-specific hybrid attention LLMs by distilling each full-attention block into a linear counterpart and greedily replacing layers under a validation-performance constraint.
-
An Efficient Self-Supervised Framework for Long-Sequence EEG Modeling
EEGM2 is a Mamba-2 integrated self-supervised model for EEG that claims linear complexity and state-of-the-art performance on long-sequence modeling and classification tasks.
-
ZONOS2 Technical Report
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing...
-
On Subquadratic Architectures: From Applications to Principles
xLSTM outperforms Mamba-2 and Gated DeltaNet on tasks with complex dependencies because its gating scheme enables more flexible and stable state tracking and memory accumulation.
-
The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency
Mamba-3 architectural changes optimized for hyperscale GPUs cause 28% higher edge latency at 880M parameters and 48% at 15M parameters compared to earlier versions.
-
ZONOS2 Technical Report
ZONOS2 8B scales a prior TTS system to 8B parameters with MoE architecture and 6M hours of data, reporting competitive benchmark performance on naturalness and speaker similarity while releasing weights.
-
Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba
A survey tracing the evolution of state-space models like S4 and Mamba, their efficiency trade-offs, and applications in NLP, vision, and other domains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.