Daniel Han

How do we maximize "luck" in reinforcement learning? Will RL finally take us to AGI and super-intelligence? What is RLVR, PPO, GRPO, Dr. GRPO, GAPO, DAPO? What are good and bad reward functions? How do we design them? How do we make RL training go fast and be memory efficient? How can quantization...

Beyond One-Size-Fits-All: Building Domain-Specific Language Models With PyTorch - Mayank Kumar, DeepTempo Double LLM RAG Accuracy by Adding GNNs - Serge Panev, NVIDIA Serving Transformers at Scale: KV-Cache-Aware Routing for PyTorch Inference - Maroon Ayoub, IBM & Tyler Michael Smith, Red Hat...

Why is Reinforcement Learning (RL) suddenly everywhere, and is it truly effective? Have LLMs hit a plateau in terms of intelligence and capabilities, or is RL the breakthrough they need? In this workshop, we'll dive into the fundamentals of RL, what makes a good reward function, and how RL can help create agents.

As open-source LLMs have become more capable, a substantial ecosystem has developed around the fine-tuning of these models. A thriving community of researchers, developers, practitioners and hobbyists has emerged which focuses on topics ranging from memory efficiency, parameter-efficient...

The story behind our 8 bug fixes for Gemma, multiple tokenization fixes for Llama 3, a sliding window bug fix and Mistral-fying Phi-3, and learn about how we analyse and find and fix bugs in open source models. Learn also how we make finetuning 2x faster for all these models

Open Models: This workshop will be split into 3x one hour blocks: 1. How to analyze & fix LLMs - how to find and fix bugs in Gemma, Phi-3, Llama & tokenizers 2. Finetuning with Unsloth - continued pretraining, reward modelling, QLoRA & more 3.