Submitted by akhaliq 26 MADLAD-400: A Multilingual And Document-Level Large Audited Dataset · 11 authors 3
Submitted by akhaliq 17 When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale · 6 authors
Submitted by akhaliq 12 Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs · 6 authors 2.64k 2
Submitted by akhaliq 9 Natural Language Supervision for General-Purpose Audio Representations · 3 authors 661
Submitted by akhaliq 6 FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning · 3 authors