Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
Paper
•
2406.16330
•
Published
•
1
Deyuan Liu
SempraETY
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
liked
a model
12 days ago
Lightricks/LTX-2
liked
a model
15 days ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Organizations
None yet
authored
2
papers
9 months ago