Saved by Andrés
The Illustrated Transformer
Why transformative artificial intelligence is really, really hard to achieve
thegradient.pub
So, there have been two breakthroughs [in AI that led to image generation tools]. One is understanding language, and the other is the ability to create images. And when you combine those things, you can create images through the understanding of language.
The Verge • “An engine for the imagination”: an interview with David Holz, CEO of AI image generator Midjourney
maintain the Transformers Python library, which is used for NLP tasks, includes implementations of state-of-the-art and popular models like Mistral 7B, BERT, and GPT-2, and is compatible with PyTorch, TensorFlow, and JAX.
Ben Auffarth • Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs
Gemma Scope Tutorial
This is a barebones tutorial on how to use Gemma Scope, Google DeepMind's suite of Sparse Autoencoders (SAEs) on every layer and sublayer of Gemma 2 2B and 9B. Sparse Autoencoders are an interpretability tool that act like a "microscope" on language model activations. They let us zoom in on dense, compressed activations, and ex... See more
This is a barebones tutorial on how to use Gemma Scope, Google DeepMind's suite of Sparse Autoencoders (SAEs) on every layer and sublayer of Gemma 2 2B and 9B. Sparse Autoencoders are an interpretability tool that act like a "microscope" on language model activations. They let us zoom in on dense, compressed activations, and ex... See more