Mixtral Fine-Tuning and Inference - Advanced Guide
Offered By: Trelis Research via YouTube
Course Description
Overview
Explore the intricacies of Mixtral fine-tuning and inference in this 34-minute video tutorial from Trelis Research. Delve into the concept of Mixture of Experts, comparing basic transformers to this advanced approach. Review the Mixtral model card, set up inference and API, and learn to run Mixtral with 4-bit quantization. Discover function calling capabilities and dive deep into fine-tuning techniques for Mixtral. Gain valuable insights on fine-tuning and inference processes, with access to various resources including GitHub repositories, Hugging Face models, and presentation slides for comprehensive understanding.
Syllabus
Mistral Mixture of Experts
Video Overview
Why Mixture of Experts?
Basic Transformer vs Mixture of Experts
Mixtral Model Card Review
Mixtral Inference and API Setup
Running Mixtral with 4 bit quantisation
Function calling Mixtral
Fine-tuning Mixtral
Notes on Fine-Tuning and Inference
Taught by
Trelis Research
Related Courses
GShard- Scaling Giant Models with Conditional Computation and Automatic ShardingYannic Kilcher via YouTube Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments
Association for Computing Machinery (ACM) via YouTube Modules and Architectures
Alfredo Canziani via YouTube Stanford Seminar - Mixture of Experts Paradigm and the Switch Transformer
Stanford University via YouTube Decoding Mistral AI's Large Language Models - Building Blocks and Training Strategies
Databricks via YouTube