From a9b7f094a2cb50f3941568c6d09731667ae8467c Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Sun, 27 Apr 2025 04:13:10 +0200 Subject: [PATCH] Update sampler_explaination.md --- sampler_explaination.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sampler_explaination.md b/sampler_explaination.md index 771390b..a3707fe 100644 --- a/sampler_explaination.md +++ b/sampler_explaination.md @@ -2,6 +2,8 @@ (made using Gemini (and read by myself so you don't just hurt yourself reading potential garbage) and re-touched a little so it's readable) +(I recommand to have the code on the side to follow) + The function _matrix\_batch\_slerp_ implements batched spherical linear interpolation (SLERP). SLERP is a technique used to interpolate between two points on a unit sphere along the great circle that connects them, maintaining a constant angular velocity. This is particularly useful for interpolating rotations or, more generally, directions in high-dimensional spaces. The function is decorated with @torch.no\_grad(), indicating that the operations within it should not be tracked for gradient computation, as it is likely used during inference or sampling. The function takes three arguments: t, which likely represents the original batch of tensors; tn, which is likely the normalized version of t; and w, which probably contains the weights or interpolation factors for each tensor in the batch. The first step inside matrix\_batch\_slerp is the calculation of dot products between all pairs of normalized tensors in tn: