view article Article Tiny Agents: an MCP-powered agent in 50 lines of code julien-c • Apr 25, 2025 • 308
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations Paper • 2109.07424 • Published Sep 15, 2021 • 1
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper • 2404.02258 • Published Apr 2, 2024 • 108