From 9fbcf97a036e6fa72b44d963aead92725506508e Mon Sep 17 00:00:00 2001
From: jinbridge <2635480475@qq.com>
Date: Wed, 12 Jun 2024 15:29:44 +0800
Subject: [PATCH] fix

---
 .../CPU/HF-Transformers-AutoModels/Model/glm4/README.md        | 2 --
 python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md     | 3 +--
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm4/README.md b/python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm4/README.md
index bc29c9f7c1b..d3d2966159c 100644
--- a/python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm4/README.md
+++ b/python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm4/README.md
@@ -31,7 +31,6 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-# install tiktoken required for GLM-4
 pip install tiktoken
 ```
 
@@ -122,7 +121,6 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-# install tiktoken required for GLM-4
 pip install tiktoken
 ```
 
diff --git a/python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md b/python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md
index 66126bb3aed..9a1cf56069d 100644
--- a/python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md
+++ b/python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md
@@ -32,7 +32,6 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-# install tiktoken required for GLM-4
 pip install tiktoken
 ```
 
@@ -68,7 +67,7 @@ In the example, several arguments can be passed to satisfy your requirements:
 - `--n-predict`: int, argument defining the max number of tokens to predict. It is default to be `32`.
 
 #### 2.4 Sample Output
-#### [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)
+##### [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)
 ```log
 Inference time: xxxx s
 -------------------- Output --------------------