Leandro Von Werra

large language model (2) code completion (1) self-supervised learning (1) knowledge distillation (1) model evaluation (1) language model training (1) code generation (1) responsible ai (1) instruction tuning (1) learning rate (1) model training (1) parameter-efficient fine-tuning (1) scaling law (1) stochastic weight averaging (1) model scaling (1) compute efficiency (1) model benchmarking (1) dataset evaluation (1) learning rate schedule (1) pretraining dataset (1)