Completed
02:36 Quantization and Mixture of Experts
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
GPT OSS Release - Inference and Fine-Tuning
Automatically move to the next video in the Classroom when playback concludes
- 1 00:00 Introduction to OpenAI's OSS Models
- 2 00:16 Model Specifications and Performance
- 3 02:36 Quantization and Mixture of Experts
- 4 04:00 MXFP8 Data Type
- 5 08:46 Running Inference on OSS Models
- 6 13:01 Fine-Tuning GPT OSS Models with transformers
- 7 24:43 Exploring Track IO Feature
- 8 26:33 ADVANCED fine-tuning tricks
- 9 27:37 Using TensorBoard for Logging
- 10 29:03 Creating a Validation Split
- 11 30:12 Inspecting the Chat Template
- 12 31:30 Preparing the Model for Training
- 13 31:47 Training Parameters and Debugging
- 14 46:41 Connecting to the Pod via SSH to git commit
- 15 49:06 Final Thoughts on OpenAI OSS Models
- 16 49:52 BONUS: Insights on Proprietary Models
