Tim Bula's picture

3 6 37

Tim Bula

timrbula

·

AI & ML interests

LLMs for language and code

Recent Activity

liked a model 5 days ago

mistralai/Mistral-Small-24B-Base-2501

reacted to singhsidhukuldeep's post with ❤️ 8 days ago

It's not every day you see a research paper named "Alice's Adventures in a Differentiable Wonderland," and when you open it, it's a 281-page book! I haven't completed it yet, but this amazing work, written by Simone Scardapane, is a fascinating introduction to deep neural networks and differentiable programming. Some key technical highlights: • Covers core concepts like automatic differentiation, stochastic optimization, and activation functions in depth • Explains modern architectures like convolutional networks, transformers, and graph neural networks • Provides mathematical foundations including linear algebra, gradients, and probability theory • Discusses implementation details in PyTorch and JAX • Explores advanced topics like Bayesian neural networks and neural scaling laws The book takes a unique approach, framing neural networks as compositions of differentiable primitives rather than biological analogs. It provides both theoretical insights and practical coding examples. I especially enjoyed the sections on: • Vector-Jacobian products and reverse-mode autodiff • Stochastic gradient descent and mini-batch optimization • ReLU, GELU, and other modern activation functions • Universal approximation capabilities of MLPs Whether you're new to deep learning or an experienced practitioner, this book offers valuable insights into the fundamentals and latest developments. Highly recommended for anyone working with neural networks!

liked a model 19 days ago

ibm-granite/granite-3.1-3b-a800m-base

View all activity

Organizations

timrbula's activity

upvoted a collection 4 months ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated Dec 18, 2024 • 95

upvoted 2 papers 6 months ago

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8, 2024 • 157

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

Paper • 2406.12034 • Published Jun 17, 2024 • 15

upvoted 2 papers 7 months ago

Scaling Granite Code Models to 128K Context

Paper • 2407.13739 • Published Jul 18, 2024 • 20

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

Paper • 2405.04324 • Published May 7, 2024 • 22

upvoted a collection 9 months ago

Granite Code Models

A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 23 items • Updated Dec 18, 2024 • 182