Shears Models (Shears: Unstructured Sparsity with Neural Low-rank Adapter Search)
-
Shears: Unstructured Sparsity with Neural Low-rank Adapter Search
Paper • 2404.10934 • Published -
Low-Rank Adapters Meet Neural Architecture Search for LLM Compression
Paper • 2501.16372 • Published • 12 -
IntelLabs/shears-llama-7b-50-math-super-adapter
Updated • 9 • 3 -
IntelLabs/shears-llama-7b-50-math-heuristic-adapter
Updated • 8 • 3