Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
GPTQ
anchor
Findings
IC-1577
Base LLMs prompted with URiAL (3 restyled in-context examples + system prompt) match or surpass their SFT/RLHF-aligned counterparts on multi-aspect evaluation
[supporting]
IC-747
SOTA pruning methods (SparseGPT, Wanda, magnitude) cause significant degradation on knowledge-intensive tasks for Vicuna and Llama models at 25-30%+ unstructured sparsity, and fail completely for n:m structured sparsity
[builds-on]
IC-747
SOTA pruning methods (SparseGPT, Wanda, magnitude) cause significant degradation on knowledge-intensive tasks for Vicuna and Llama models at 25-30%+ unstructured sparsity, and fail completely for n:m structured sparsity
[compared-to]
IC-748
Pruned LLMs at ≥50% sparsity remain robust in-context retrievers and summarizers, with Vicuna-7B matching up to ~40% sparsity and Vicuna-13B up to ~50% sparsity in open-book settings
[primary]