# Efficient distillation

An efficient text-to-image model series distilled from mainstream diffusion models on AMD Instinct™ GPUs

LaMini-Flan-T5-783M is an instruction-following model fine-tuned on the LaMini-instruction dataset based on google/flan-t5-large, with 783M parameters, belonging to the LaMini-LM series.

MiniLM is a compact and efficient pre-trained language model that compresses Transformer models through deep self-attention distillation technology, supporting multilingual understanding and generation tasks.