Model Efficiency, Instruction Prioritization, and Workflow Automation

23/04/2024 11 min Episodio 14
Model Efficiency, Instruction Prioritization, and Workflow Automation

Listen "Model Efficiency, Instruction Prioritization, and Workflow Automation"

Episode Synopsis


Phi-3 Technical Report: A Highly Capable Language Model Locally on Your PhoneThe Instruction Hierarchy: Training LLMs to Prioritize Privileged InstructionsFlowMind: Automatic Workflow Generation with LLMsMusic Consistency ModelsHow Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study

More episodes of the podcast AI Papers Podcast