MoraxGeo

Sherry-1B-1.25bit-per-channel

MoraxGeo/Sherry-1B-1.25bit-per-channel

Sherry-1B-1.25bit-per-channel is a machine learning model from MoraxGeo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.2.

A reproduced 1.25bit 1B model based on LLaMA-3.2 with Sherry quantization method from the paper: Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification