LLMs on Yale's clusters

This workshop will provide researchers interested in LLMs with the skills to launch and run inference-based workflows with open-source models on YCRC systems. Specifically, attendees will learn: What GPU resources are available for each YCRC systemHow to identify what GPU is needed for different LLMsHow to launch an LLM on YCRC systemsHow to conduct inference via direct prompting with an LLM using ollamaHow to modify an LLM's parameters for reproducibility/consistency in responseHow to implement an LLM within python using jupyter and ollamaAdditional considerations for RAG and fine-tuning. This is an advanced instruction. Working introductory knowledge of HPC on Yale's clusters is required.