Ternary Mamba-2 1.3B models reach 48.1% zero-shot accuracy via QAT from pretrained checkpoints in 102M tokens, close to Bi-Mamba, with 3.61x compression.
TernaryLLM: Ternarized Large Language Model
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
TWLA is a PTQ method using E2M-ATQ, KOTMS, and ILA-AMP to enable W1.58A4 quantization for LLMs with maintained accuracy.
A formalized design-space framework with generator and TSMC 16nm-validated cost model shows that LUT reuse gains depend on activation type and that larger cores improve density, yielding 2.2x area reduction over multiplier baselines.
CAT-Q performs post-training ternary quantization of 1.7B-235B LLMs with 512 samples via learnable modulation and softened ternarization, outperforming BitNet v1/v2 models trained on 100B tokens.
VCON is a unified framework for smooth iterative DNN compression that uses parallel execution and an affine combination to progressively replace the original model with its compressed form during fine-tuning.
citing papers explorer
-
Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models
Ternary Mamba-2 1.3B models reach 48.1% zero-shot accuracy via QAT from pretrained checkpoints in 102M tokens, close to Bi-Mamba, with 3.61x compression.
-
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
TWLA is a PTQ method using E2M-ATQ, KOTMS, and ILA-AMP to enable W1.58A4 quantization for LLMs with maintained accuracy.
-
Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference
A formalized design-space framework with generator and TSMC 16nm-validated cost model shows that LUT reuse gains depend on activation type and that larger cores improve density, yielding 2.2x area reduction over multiplier baselines.
-
CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
CAT-Q performs post-training ternary quantization of 1.7B-235B LLMs with 512 samples via learnable modulation and softened ternarization, outperforming BitNet v1/v2 models trained on 100B tokens.
-
Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
VCON is a unified framework for smooth iterative DNN compression that uses parallel execution and an affine combination to progressively replace the original model with its compressed form during fine-tuning.