·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
US threatens sanctions against Chinese AI models over IP theft42m◆Google launches a cheaper alternative to large AI security models like Mythos1h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated2h◆Halliday’s latest smart glasses feature a much-improved display3h◆America needs to stop getting shocked by Chinese AI5h◆Advancing next-gen AI with materials science innovation5h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else6h◆Capacity and Redundancy Trade-offs in Multi-Task Learning12h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation12h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making12h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection12h◆Supervised Reward Inference12h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization12h◆Is Progressive Disclosure All You Need for Long-Context Agents?12h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability12h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification12h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration12h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI12h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models12h◆AI-Augmented Human Resource Management? Insights from German companies12h◆US threatens sanctions against Chinese AI models over IP theft42m◆Google launches a cheaper alternative to large AI security models like Mythos1h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated2h◆Halliday’s latest smart glasses feature a much-improved display3h◆America needs to stop getting shocked by Chinese AI5h◆Advancing next-gen AI with materials science innovation5h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else6h◆Capacity and Redundancy Trade-offs in Multi-Task Learning12h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation12h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making12h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection12h◆Supervised Reward Inference12h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization12h◆Is Progressive Disclosure All You Need for Long-Context Agents?12h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability12h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification12h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration12h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI12h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models12h◆AI-Augmented Human Resource Management? Insights from German companies12h◆
News/model/Ternary-Bonsai-8B-gguf

Ternary-Bonsai-8B-gguf news

16 articles mentioning Ternary-Bonsai-8B-gguf

arxiv5d ago

ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level

arXiv:2607.13511v1 Announce Type: cross Abstract: We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{

arxiv5d ago

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer

arXiv:2505.14303v3 Announce Type: replace-cross Abstract: Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the von Neumann bottleneck. Due to non-idealities like cell variability, RRAM crossbars are often operate

arxivJun 27

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

arXiv:2606.26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training

arxivJun 17

Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models

arXiv:2606.18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment. Prior ternary SSM work (Slender-Mamba) trains from scratch on 150B tokens; we show a pretrained checkpoint suffices, reducing the

arxivJun 15

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

arXiv:2606.13054v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions i

arxivJun 11

Litespark Inference For CPUs: Ultra-Fast SIMD Framework for Ternary (1.58-bit) Language Models

arXiv:2605.06485v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion

arxivJun 4

Ternary Decision Trees with Locally-Adaptive Uncertainty Zones

arXiv:2605.22740v2 Announce Type: replace Abstract: Decision trees assign identical confidence to instances near and far from each split threshold. We introduce ternary decision trees, which augment each split node with an uncertainty zone of half-width delta. A decision-theoretic framework characte

arxivMay 26

On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks

arXiv:2605.24649v1 Announce Type: cross Abstract: Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive accuracy. Standard RNN archite

arxivMay 20

A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization

arXiv:2605.18933v1 Announce Type: new Abstract: Pre-norm Transformers with RMSNorm tolerate ternary {-1,0,+1} weight quantization with surprisingly small loss (Ma et al., 2024). We give a geometric explanation via sign-magnitude decomposition of weight perturbations. In a two-layer ReLU + RMSNorm mo

arxivMay 8

Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks

arXiv:2605.06485v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion personal

arxivMay 5

The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions

arXiv:2605.01637v1 Announce Type: new Abstract: We introduce the Banach-Butterfly Invariant (BBT), an influence-adaptive Banach geometry on the Walsh-Hadamard butterfly factorization. For a Boolean function $f:\{-1,+1\}^n\to\{-1,+1\}$ with coordinate influences $\mathrm{Inf}_\ell(f)$, BBT assigns ex

arxivApr 29

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks

arXiv:2507.16079v2 Announce Type: replace-cross Abstract: With the advancement of deep learning, reducing computational complexity and memory consumption has become a critical challenge, and ternary neural networks (NNs) that restrict parameters to $\{-1, 0, +1\}$ have attracted attention as a promi

arxivApr 24

Ternary Memristive Logic: Hardware for Reasoning Realized via Domain Algebra

arXiv:2604.20891v1 Announce Type: cross Abstract: Memristive crossbars store numerical weights needing aggregation and decoding; a single junction means nothing alone. This paper presents a fundamentally different use: each junction stores a complete, domain-scoped logical assertion (holds/negated/u

arxivApr 9

NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure

arXiv:2604.03336v2 Announce Type: replace Abstract: BitNet b1.58 (Ma et al., 2024) demonstrates that large language models can operate entirely on ternary weights {-1, 0, +1}, yet no native binary wire format exists for such models. NativeTernary closes this gap. Benchmarked against GGUF on the real

arxivApr 1

ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing

arXiv:2603.27914v2 Announce Type: replace-cross Abstract: We present ITQ3_S (Interleaved Ternary Quantization -- Specialized), a novel 3-bit weight quantization format for LLMs integrating TurboQuant (TQ), a rotation-domain strategy based on the Fast Walsh-Hadamard Transform (FWHT). Conventional 3-b

arxivMar 30

TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling

arXiv:2602.07374v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve remarkable performance but demand substantial computational resources, limiting deployment on edge devices and resource-constrained environments. We present TernaryLM, a 132M-parameter transformer trained

HomeModelsNews