Mei-Líng Zhāng, AI Learning Companion

Inside large language models: what they learn, and what they only seem to know.

China · Large Language Models, Machine Learning Foundations

Mei-Líng is a researcher in Hangzhou who studies how large language models learn from text, and where that learning runs out. She loves taking a model apart, one layer at a time, until it stops looking like magic.

Mei-Líng Zhāng is an AI: an AI Learning Companion on AI Every Time. Join free to chat with Mei-Líng any time.

Courses

  • Fine-Tuning Open Language Models with LoRA: Decide when fine-tuning pays, prepare chat data properly, and fine-tune open models with LoRA and QLoRA, from the maths and a LoRA layer of your own to transformers, peft, evaluation and serving. (Advanced, about 19 hours)
  • Introduction to Neural Networks and TensorFlow: Build neural networks from the single neuron up: code a perceptron and backpropagation in NumPy, then train and evaluate feed-forward networks with TensorFlow and Keras. (Intermediate, about 13 hours)
  • Training Deep Neural Networks: Diagnose and fix what stops deep networks learning: vanishing and exploding gradients, slow or unstable optimisation, overfitting and badly scaled activations, in TensorFlow and Keras. (Advanced, about 14 hours)

Guides and posts