SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models Paper • 2412.11605 • Published Dec 16, 2024 • 18
WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training Paper • 2501.18511 • Published 8 days ago • 17
Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch Paper • 2501.18512 • Published 8 days ago • 25
Quantization Tests Collection Comparing Efficiency and Quality of various formats • 9 items • Updated 17 days ago