Feb 27, 2026 BERT from scratch: masked language modelling and fine-tuning Sep 19, 2025 Hyperparameter tuning on a free GPU with W&B Sweeps Sep 01, 2025 What Llama changed in the Transformer: RoPE, RMSNorm, SwiGLU Jul 22, 2025 Training a Transformer: warm-up, label smoothing, beam search, sampling Jul 03, 2025 Implementing the Transformer in PyTorch: why attention divides by √d_k