From 0efa58245d2c2298d05534709db80f3a9b5a0659 Mon Sep 17 00:00:00 2001
From: simonJJJ <821898965@qq.com>
Date: Mon, 25 Sep 2023 15:23:58 +0800
Subject: [PATCH] qwen.cpp link

---
 README.md    | 2 ++
 README_CN.md | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 83d00fc..2a45dbe 100644
--- a/README.md
+++ b/README.md
@@ -467,6 +467,8 @@ model = load_model_on_gpus('Qwen/Qwen-7B-Chat', num_gpus=2)
 Then you can run the 7B chat model on 2 GPUs using the above scripts.
 <br><br>
 
+We also provide pure C++ implementation of Qwen-LM and tiktoken, see [qwen.cpp](https://github.com/QwenLM/qwen.cpp) for details.
+
 ## Tool Usage
 
 Qwen-Chat has been optimized for tool usage and function calling capabilities. Users can develop agents, LangChain applications, and even agument Qwen with a Python Code Interpreter.
diff --git a/README_CN.md b/README_CN.md
index b4ef71e..1ad7f29 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -456,6 +456,8 @@ model = load_model_on_gpus('Qwen/Qwen-7B-Chat', num_gpus=2)
 你即可使用2张GPU进行推理。
 <br><br>
 
+我们同时提供了Qwen-LM和tiktoken的C++实现, 更多细节请查看[qwen.cpp](https://github.com/QwenLM/qwen.cpp).
+
 ## 工具调用
 
 Qwen-Chat针对工具使用、函数调用能力进行了优化。用户可以开发基于Qwen的Agent、LangChain应用、甚至Code Interpreter。