Quantization usually causes modest information loss and reduced factual knowledge recall in LLMs, especially smaller ones, but BitSandBytes preserves performance best and occasional gains occur.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Moderate pruning of MoE models preserves in-domain biomedical utility and reliability but both degrade rapidly in cross-domain settings and at extreme pruning ratios.
citing papers explorer
-
Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
Quantization usually causes modest information loss and reduced factual knowledge recall in LLMs, especially smaller ones, but BitSandBytes preserves performance best and occasional gains occur.
-
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
Moderate pruning of MoE models preserves in-domain biomedical utility and reliability but both degrade rapidly in cross-domain settings and at extreme pruning ratios.