d-matrix/Llama-3.2-1B

d-matrix/Llama-3.2-1B is a 1 billion parameter functional reference model from d-Matrix, based on the Llama 3.2 architecture. It provides configurations including a baseline equivalent to the original model and a 'BASIC' version with all linear algebraic operands quantized to MXINT8-64. This model is designed for evaluating the impact of d-Matrix's Dmx_Compressor on Llama 3.2-1B, focusing on quantization and functional equivalence.