Completed
Self-Rewarding Language Architecture
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Fine-Tuning Self-Rewarding Language Models with Mistral 7B
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Self-Rewarding Language Architecture
- 3 Fine-Tuning Scripts
- 4 Data for Fine-Tuning
- 5 Supervised Fine-Tuning Script
- 6 High Lora Alpha and Quantization
- 7 Evaluation Fine-Tuning Data
- 8 Generating New Prompts
- 9 Live Demo of Prompt Gen
- 10 Generating Responses
- 11 Generating Scores
- 12 Config, Compute, and Cost
- 13 Analyzing Scores
- 14 Live Run of DPO
