Submitted by xcjthu 13 InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation OpenBMB 2
4 Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data OpenBMB
Submitted by fengyao1909 30 Configurable Foundation Models: Building LLMs from a Modular Perspective OpenBMB 2