From 42dc77793f55a72da1f876a67c15b3b03e5faa95 Mon Sep 17 00:00:00 2001
From: gaoyang07 <Gary1546308416AL@gmail.com>
Date: Fri, 19 Jan 2024 19:29:22 +0800
Subject: [PATCH] update README in tools

---
 tools/README.md | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/README.md b/tools/README.md
index f9b69eb..37bf7af 100644
--- a/tools/README.md
+++ b/tools/README.md
@@ -1,9 +1,14 @@
 # InternLM2 tools
 
-## Convert to LLaMA
+## 1. Convert to LLaMA
 
-`convert2llama.py` can convert InternLM2 to LLaMA:
+We offer the `convert2llama.py`, designed to seamlessly transform InternLM2 (HF format) into LLaMA (HF format). Here, HF refers to the format used by HuggingFace Transformers.
 
+### Usage
 ```
-python convert2llama.py --src /path/to/internlm2 --tgt /path/to/target
+python convert2llama.py --src /path/to/internlm2/ckpt --tgt /path/to/target/ckpt
 ```
+
+### Note
+
+While the `convert2llama.py` tool is available, we still advise opting for InternLM2 when practical, chiefly due to its superior efficiency. InternLM2, which is adapted from LLaMA, streamlines the process by integrating the `Wq`, `Wk`, `Wv` weight matrices into a single matrix `Wqkv`. This integration leads to approximately a **5%** speed increase during training. Given the substantial costs associated with pre-training, this efficiency boost can result in significant savings.