Search Results for author:
Found 2 papers, 0 papers with code
FoldGPT: Simple and Effective Large Language Model Compression Scheme
Based on this observation, we propose an efficient model volume compression strategy, termed FoldGPT, which combines block removal and block parameter sharing. This strategy consists of three parts: (1) Based on the learnable gating parameters, we determine the block importance ranking while modeling the coupling effect between blocks.
Differentiable Search for Finding Optimal Quantization Strategy
To solve the issue, in this paper, we propose a differentiable quantization strategy search (DQSS) to assign optimal quantization strategy for individual layer by taking advantages of the benefits of different quantization algorithms.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
