Democratizing Foundation Models via k-bit Quantization - Tim Dettmers | Stanford MLSys #82 Published 2023-10-23 Download video MP4 360p Download video MP4 720p Recommendations 55:59 Training LLMs at Scale - Deepak Narayanan | Stanford MLSys #83 56:32 Monarch Mixer: Making Foundation Models More Efficient - Dan Fu | Stanford MLSys #86 10:32 Why Elon Musk is Afraid of Artificial Intelligence | Insights from 'Superintelligence' Nick Bostrom 17:07 LoRA explained (and a bit about precision and quantization) 30:48 QLoRA: Efficient Finetuning of Quantized LLMs | Tim Dettmers 58:41 8-bit Methods for Efficient Deep Learning with Tim Dettmers 45:32 A Survey of Techniques for Maximizing LLM Performance 55:51 Your Microbiome: What Is It, and How Can It Help or Hurt You? 59:17 Serving 100s of LLMs on 1 GPU with LoRAX - Travis Addair | Stanford MLSys #84 1:16:48 Notes on AI Hardware - Benjamin Spector | Stanford MLSys #88 52:02 NWDS Talk - From Text2SQL to Automating BI: The Coming Wave of LLM Analytic Agents 1:27:21 CBMM10 Panel: Research on Intelligence in the Age of AI 1:04:31 MedAI #78: Foundation Models for Medical AI | Vivek Natarajan 1:11:41 Stanford CS25: V2 I Introduction to Transformers w/ Andrej Karpathy 1:01:53 Tim Dettmers | QLoRA: Efficient Finetuning of Quantized Large Language Models 58:13 How Fine-tuning Open Source LLMs Solves GenAI Productionization - Piero Molino | Stanford MLSys #94 42:06 Understanding 4bit Quantization: QLoRA explained (w/ Colab) 1:13:13 Robert Sapolsky: The Biology of Humans at Our Best and Worst 55:01 Scaling Up “Vibe Checks” for LLMs - Shreya Shankar | Stanford MLSys #97 1:02:50 MIT 6.S191 (2023): Recurrent Neural Networks, Transformers, and Attention Similar videos 06:46 Tim Dettmers—k-bit Inference Scaling Laws 52:56 Multimodal Reasoning: PaLM-E & Gemini - Aakanksha Chowdhery | Stanford MLSys #90 47:47 8-bit Methods for Efficient Deep Learning -- Tim Dettmers (University of Washington) 12:16 8-bit Optimizers via Block-wise Quantization 58:29 A Taxonomy of ML for Systems Problems - Martin Maas | Stanford MLSys #81 58:07 ML for ML Compilers - Mangpo Phothilimthana | Stanford MLSys #80 57:58 QLoRA: Efficient Finetuning of Quantized Large Language Models (Tim Dettmers) 58:41 A data-centric view on reliable generalization - Ludwig Schmidt | Stanford MLSys #71 1:06:53 AI on your phone? Tim Dettmers on quantization of neural networks — #41 26:49 MLT __init__ Session #17: LLM int8 3:06:41 QLoRA: Quantization for Fine Tuning 38:10 Panel discussion #1 | with Tim Dettmers, Johnathan Frankle, Julien Launay and Ce Zhang 45:22 LLMs for Everything and Everyone! - Sebastian Raschka - Lightning AI 1:12:37 Tim Dettmers: Personal Side of Academia, How to pick your Grad School, RTX 3000 FAQ 1:19:36 [Ambient AI] Lecture 5: Deep neural network quantization (1) More results