Mengliu Zhao

A year-end summary for junior-level MLE interview preparation Mengliu Zhao · Follow Published in Towards Data Science · 14 min read · 9 hours ago — Job-seeking is hard! In today’s market, job-seeking for machine learning-related roles is more complex than ever. Even though public reports claim that the job demand for machine learning engineers (MLE) is fast growing, the fact is that the market has turned toward an employer’s market over the past few

On multi-modal LLM Flamingo’s vision encoder Mengliu Zhao · Follow Published in Towards Data Science · 5 min read · 7 hours ago — Designing Multi-modal LLM is hard. The state-of-the-art multi-modal LLMs are primarily based on existing LLM architectures, with modifications specifically addressing different sources of input, and that’s where the difficulty comes from. The latest Nvidia paper divides the commonly used multi-modal architectures into two categories: decoder-based; cross-attention-based. One of my previous medium

How to get 2X speed up model training using three lines of code Mengliu Zhao · Follow Published in Towards Data Science · 8 min read · 6 hours ago — Have you ever wished your deep-learning model could run faster? The GPU is expensive. The dataset is enormous, and the training session seems endless; you have a million experiments to run and a deadline to hit — all these are good reasons to expect

A gentle introduction to the latest multi-modal transfusion model Mengliu Zhao · Follow Published in Towards Data Science · 6 min read · 7 hours ago — Recently, Meta and Waymo released their latest paper — Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model, which integrates the popular transformer model with the diffusion model for multi-modal training and prediction purposes. Like Meta’s previous work, the Transfusion model is based on the

A deep dive into PyTorch DataLoader with Multiprocessing Mengliu Zhao · Follow Published in Towards Data Science · 6 min read · 2 hours ago — As one of the many who use the PyTorch library on a day-to-day basis, I believe many ML engineer sooner or later encounters the problem “DataLoader worker (pid(s) xxx) exited unexpectedly” during training. It’s frustrating. This error is often triggered when calling the DataLoader with parameter num_workers > 0.