From e1175b83140a642b0f1cd06b9c9535562bb98115 Mon Sep 17 00:00:00 2001
From: klosax <131523366+klosax@users.noreply.github.com>
Date: Mon, 7 Aug 2023 18:27:49 +0200
Subject: [PATCH] README.md : Add info about using linear rope scaling

---
 examples/main/README.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/examples/main/README.md b/examples/main/README.md
index 014112e5d..55c16096f 100644
--- a/examples/main/README.md
+++ b/examples/main/README.md
@@ -140,6 +140,12 @@ The `--ctx-size` option allows you to set the size of the prompt context used by
 
 -   `-c N, --ctx-size N`: Set the size of the prompt context (default: 512). The LLaMA models were built with a context of 2048, which will yield the best results on longer input/inference. However, increasing the context size beyond 2048 may lead to unpredictable results.
 
+### Extended Context Size
+
+Some fine-tuned models have extened the context length by scaling RoPE. For example, if the original pretrained model have a context length (max sequence length) of 4096 (4k) and the fine-tuned model have 32k. That is a scaling factor of 8, and should work by setting the above `--ctx-size` to 32768 (32k) and `--rope-scale` to 8.
+
+- `--rope-scale N`: Where N is the linear scaling factor used by the fine-tuned model.
+
 ### Keep Prompt
 
 The `--keep` option allows users to retain the original prompt when the model runs out of context, ensuring a connection to the initial instruction or conversation topic is maintained.