Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math

Vídeos relacionados

19:39

What is RLHF?

18k • 1 year ago

22:13

The Elo Rating System

198k • 1 year ago

1:14:29

Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, Math

62k • 2 years ago

38:24

Proximal Policy Optimization (PPO) - How to train Large Language Models

85k • 2 years ago

2:15:13

Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.

71k • 2 years ago

21:15

Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning

34k • 1 year ago

16:57

Direct Preference Optimization (DPO) | Paper Explained

2.3k • 5 months ago

1:00:15

ML Interpretability: feature visualization, adversarial example, interp. for language models

12k • 2 years ago

1:12:53

Distributed Training with PyTorch: complete tutorial with cloud infrastructure and code

38k • 2 years ago

1:09:00

[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

171k • 1 year ago

1:18:44

Stanford CS234 I Guest Lecture on DPO: Rafael Rafailov, Archit Sharma, Eric Mitchell I Lecture 9

12k • 1 year ago

27:12

Variational Autoencoder - Model, ELBO, loss function and maths explained easily!

70k • 2 years ago