kosbu/Athene-V2-Chat-AWQ

Athene-V2-Chat AWQ 4-Bit Quantized Version

This repository provides the AWQ 4-bit quantized version of the Athene-V2-Chat model, originally developed by Nexusflow. This model's weights are padded with zeros before quantization to ensure compatibility with multi-GPU tensor parallelism by resolving divisibility constraints. The padding minimally impacts computation while enabling efficient scaling across multiple GPUs.