Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"
There are two args to handle calibration dataset, this may confuse the users. Let's transfer all the combability of dataloader to dataset, and delete dataloader
There are two args to handle calibration dataset, this may confuse the users. Let's transfer all the combability of dataloader to dataset, and delete dataloader