From 4f8d62e4442392b38a56f75b8980e2b3558cafc4 Mon Sep 17 00:00:00 2001
From: akawrykow <a.kawrykow@gmail.com>
Date: Tue, 22 Aug 2023 17:48:48 -0700
Subject: [PATCH] Add --ctx param to Prepare Data & Run section

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 92420bbd4..c16eced41 100644
--- a/README.md
+++ b/README.md
@@ -514,7 +514,8 @@ ls ./models
 python3 -m pip install -r requirements.txt
 
 # convert the 7B model to ggml FP16 format
-python3 convert.py models/7B/
+# Use --ctx 4096 for LLaMA v2
+python3 convert.py models/7B/ --ctx 2048
 
   # [Optional] for models using BPE tokenizers
   python convert.py models/7B/ --vocabtype bpe