ISTA-DASLab/DeepSeek-V3-0324-GPTQ-4b-128g-experts
Text Generation • 104B • Updated
• 89 • 3
None defined yet.
MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers