Tag: tokens
-
From Tokens to Theorems: Building a Neuro-Symbolic AI Mathematician
From Tokens to Theorems: Building a Neuro-Symbolic AI Mathematician The next Gauss may not be born — they may be spun up in the cloud The post From Tokens to Theorems: Building a Neuro-Symbolic AI Mathematician appeared first on Towards Data Science. Sean Moran Go to original source
-
How to Train LLMs to “Think” (o1 & DeepSeek-R1)
How to Train LLMs to “Think” (o1 & DeepSeek-R1) In September 2024, OpenAI released its o1 model, trained on large-scale reinforcement learning, giving it “advanced reasoning” capabilities. Unfortunately, the details of how they pulled this off were never shared publicly. Today, however, DeepSeek (an AI research lab) has replicated this reasoning behavior and published the…
-
Beyond Causal Language Modeling
Beyond Causal Language Modeling A deep dive into “Not All Tokens Are What You Need for Pretraining” Introduction A few days ago, I had the chance to present at a local reading group that focused on some of the most exciting and insightful papers from NeurIPS 2024. As a presenter, I selected a paper titled…