JoaoLages

Maybe you've heard about this technique but you haven't completely understood it, especially the PPO part. This explanation might help.

We will focus on text-to-text language models 📝, such as GPT-3, BLOOM, and T5. Models like BERT, which are encoder-only, are not addressed.

Reinforcement Learning from Human Feedback (RLHF) has been successfully applied in ChatGPT, hence its major increase in popularity. 📈

RLHF is especially useful in two scenarios 🌟:

• You can’t create a good loss function
  • Example: how do you calculate a metric to measure if the model’s output was funny?
• You want to train with production data, but you can’t easily label your production data

munrocket

WGSL Noise Algorithms

Good and fast integer hash

// https://www.pcg-random.org/
fn pcg(n: u32) -> u32 {
    var h = n * 747796405u + 2891336453u;
    h = ((h >> ((h >> 28u) + 4u)) ^ h) * 277803737u;
    return (h >> 22u) ^ h;
}