From 62cfc54f77e519057110265b52b0d614fa363e2a Mon Sep 17 00:00:00 2001
From: unbounded <haakon@likedan.net>
Date: Sat, 8 Apr 2023 00:09:18 +0200
Subject: Add quantize-stats command for testing quantization (#728)

Command that calculates some statistics over the errors introduced by
quantization, like mean square error, max error and some percentile errors for layer
weights. Should be useful for testing quantization improvements.

Exposes some internal state from ggml and llama for testing
---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to '.gitignore')

diff --git a/.gitignore b/.gitignore
index a052543..d8dd34f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,6 +19,7 @@ models/*
 
 /main
 /quantize
+/quantize-stats
 /result
 /perplexity
 /embedding
-- 
cgit v1.2.3