From b8ba25f5e9f6be189407cb551aed7ed33a559857 Mon Sep 17 00:00:00 2001
From: alquist4121 <45760211+sekizawaryo@users.noreply.github.com>
Date: Mon, 31 Jul 2023 00:27:41 +0900
Subject: [PATCH] fix explanation

---
 examples/nllb200_3B_8bit.sh | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/examples/nllb200_3B_8bit.sh b/examples/nllb200_3B_8bit.sh
index c56c482..50c8c30 100644
--- a/examples/nllb200_3B_8bit.sh
+++ b/examples/nllb200_3B_8bit.sh
@@ -1,5 +1,8 @@
-# Run NLLB200-3B model on sample text. We use FP16 precision, which requires a GPU with a lot of VRAM
-# For running this model in GPUs with less VRAM, use 8-bit quantization, see examples/nllb200_3B_8bit.sh
+# Run  NLLB200-3B on sample text. This model requires a GPU with a lot of VRAM, so we use
+# 8-bit quantization to reduce the required VRAM so we can fit in customer grade GPUs. If you have a GPU
+# with a lot of RAM, running the model in FP16 should be faster and produce sighly better results,
+# see examples/nllb200-3B_fp16.sh
+
 
 python3 translate.py \
 --sentences_path sample_text/en.txt \