If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
Paper
•
2412.04144
•
Published
•
5
•
2
Muhammad Khalifa
mkhalifa
AI & ML interests
natural language genration, reinforcement learning
Recent Activity
updated
a model
about 14 hours ago
mkhalifa/qwen_14b_longthought-1K
published
a model
about 15 hours ago
mkhalifa/qwen_14b_longthought-1K
updated
a model
2 days ago
mkhalifa/r1_14b_longthought-1K
Organizations
None yet
mkhalifa's activity
commented
a
paper
3 months ago
The dataset solutions have many typos
#2 opened 4 months ago
by
mkhalifa