AI: SliceGPT: Compress Large Language Models by Deleting Rows and Columns — “SliceGPT can remove up to 25% of the model parameters (including embeddings) for LLAMA2-70B, OPT 66B and Phi-2 models while maintaining 99%, 99% and 90% zero-shot task performance…Our sliced models run on fewer GPUs and run faster without any additional code optimization…”
Links for 2024-01-31
Links for 2024-01-31
Links for 2024-01-31
AI: SliceGPT: Compress Large Language Models by Deleting Rows and Columns — “SliceGPT can remove up to 25% of the model parameters (including embeddings) for LLAMA2-70B, OPT 66B and Phi-2 models while maintaining 99%, 99% and 90% zero-shot task performance…Our sliced models run on fewer GPUs and run faster without any additional code optimization…”