Thought, the LLM can verbalize that the unknown city is Paris and use this fact to answer downstream questions.

Large Language Models (LLMs) have long held sway in the realm s of artificial intelligence research. Numerous efficient techniques, inc luding weight pruning, quantization, and distillation, have been embraced to comp ress LLMs, targeting memory reduction and inference acceleration, which unders core the redundancy in LLMs. However, most model compression techniques concen trate on weight optimization, overlooking the exploration of optimal arch itectures. Besides, traditional architecture search methods, limited by the eleva ted complexity with extensive parameters, struggle to demonstrate their effecti veness on LLMs. In this paper, we propose a training-free architecture search fram ework to identify optimal subnets that preserve the fundamental strengths of the o riginal LLMs while achieving inference acceleration. Furthermore, after gen erating subnets that inherit specific weights from the original LLMs, we introduce a reformation algorithm that utilizes the omitted weights to rectify the inher ited weights with a small amount of calibration data. Compared with SOT A training-fr ee structured pruning works that can generate smaller networks, our method dem onstrates superior performance across standard benchmarks. Furthermore, our generated subnets can directly reduce the usage of GPU memory and achieve infer ence acceleration.

These features are then fed into a V alue Classification Network (VCN) which directly generates classification solutions.