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.
Mixtral Fine-Tuning and Inference - Advanced Guide
Overview
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
-
Fine-Tuning LLM Models - Generative AI Course
-
The Best Tiny Language Models - Performance, Fine-tuning, and Function-calling
-
Fine-tuning Language Models for Structured Responses with QLoRa - Lecture
-
Embeddings vs Fine-Tuning - Supervised Fine-tuning - Part 2
-
Very Few Parameter Fine-Tuning with ReFT and LoRA
-
Really Long Context LLMs - 200k Input Tokens
