20 articles mentioning Ternary-Bonsai-27B-gguf
arXiv:2609.00224v2 Announce Type: replace-cross Abstract: Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2
arXiv:2608.29069v1 Announce Type: cross Abstract: Operator-learning surrogates have been benchmarked largely on single-field, single-interface problems, leaving unclear whether architectural choices validated in those settings transfer to constrained, multiphase flows. We introduce a three-phase int
arXiv:2608.28809v1 Announce Type: new Abstract: Extreme low-bit inference offers a route toward smaller models and constrained deployment. Ternary language models restrict weights to $\{-1,0,+1\}$, approaching the limit of $\log_2 3 \approx 1.585$ bits/weight. The practical question for a pretrained
arXiv:2607.22143v1 Announce Type: new Abstract: Molecular glue degraders have emerged as a promising strategy for targeted protein degradation by inducing ternary complex formation between an E3 ubiquitin ligase and a target protein. Despite their therapeutic potential, computational design of molec
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
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 \{
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
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
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
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
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
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
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
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
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
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
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
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
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
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