ISTA-DASLab/Llama-3.2-1B-AQLM-PV-2Bit-2x8
Text Generation
•
0.5B
•
Updated
•
10
None defined yet.
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization