July 25th, 2023 - Byte-Sized Brilliance: Decoding the Epochs of ML Evolution
MP3•Episode home
Manage episode 372191015 series 3485608
Content provided by Marcus Edel. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Marcus Edel or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
- The case for 4-bit precision: k-bit Inference Scaling Laws
- No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
- PUMA: Secure Inference of LLaMA-7B in Five Minutes
- Optimized Network Architectures for Large Language Model Training with Billions of Parameters
- A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Chapters
1. Intro (00:00:00)
2. The case for 4-bit precision: k-bit Inference Scaling Laws (00:01:28)
3. No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models (00:04:15)
4. PUMA: Secure Inference of LLaMA-7B in Five Minutes (00:06:02)
5. Optimized Network Architectures for Large Language Model Training with Billions of Parameters (00:08:33)
6. A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis (00:09:53)
75 episodes