tangles/Qwen3.8-27B-Uncensored-NVFP4-v100-skinny Image-Text-to-Text • 18B • Updated 3 days ago • 221 • 2
Snowflake/snowflake-arctic-embed-m-v2.0 Sentence Similarity • 0.3B • Updated Apr 24, 2025 • 80.3k • 108
view article Article Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach oopere • Nov 24, 2024 • 24
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging Paper • 2406.16330 • Published Jun 24, 2024 • 1