ISTA-DASLab/Llama-3.2-3B-AQLM-PV-2Bit-2x8
Text Generation
•
1B
•
Updated
•
9
None defined yet.
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training