ISTA-DASLab/Llama-2-70b-AQLM-4Bit-2x16-hf
Text Generation • 18B • Updated • 11
None defined yet.
MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers