Limit trl version in example (#12332)

* Limit trl version in example

* Limit trl version in example

python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm-4v/README.md

@@ -19,7 +19,7 @@ conda activate llm
 # install ipex-llm with 'all' option
 pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
 
-pip install torchvision tiktoken transformers==4.42.4 trl
+pip install torchvision tiktoken transformers==4.42.4 "trl<0.12.0"
 ```
 
 On Windows:
@@ -30,7 +30,7 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-pip install torchvision tiktoken transformers==4.42.4 trl
+pip install torchvision tiktoken transformers==4.42.4 "trl<0.12.0"
 ```
 
 ### 2. Run

python/llm/example/CPU/HF-Transformers-AutoModels/Model/glm4/README.md

@@ -18,7 +18,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 On Windows:
@@ -29,7 +29,7 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 ## 2. Run

python/llm/example/CPU/HF-Transformers-AutoModels/Model/llama3.1/README.md

@@ -20,7 +20,7 @@ pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pyt
 
 # transformers>=4.43.1 is required for Llama3.1 with IPEX-LLM optimizations
 pip install transformers==4.43.1
-pip install trl 
+pip install "trl<0.12.0" 
 ```
 On Windows:
 
@@ -31,7 +31,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[all]
 
 pip install transformers==4.43.1
-pip install trl 
+pip install "trl<0.12.0" 
 ```
 
 ### 2. Run

python/llm/example/CPU/HF-Transformers-AutoModels/Model/minicpm-v-2_6/README.md

@@ -18,7 +18,7 @@ conda activate llm
 # install ipex-llm with 'all' option
 pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
 pip install torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cpu
-pip install transformers==4.40.0 trl
+pip install transformers==4.40.0 "trl<0.12.0"
 ```
 On Windows:
 
@@ -28,7 +28,7 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 pip install torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cpu
-pip install transformers==4.41.0 trl
+pip install transformers==4.41.0 "trl<0.12.0"
 ```
 
 ### 2. Run

python/llm/example/CPU/PyTorch-Models/Model/glm4/README.md

@@ -21,7 +21,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 On Windows:
@@ -32,7 +32,7 @@ conda activate llm
 
 pip install --pre --upgrade ipex-llm[all]
 
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 ### 2. Run

python/llm/example/GPU/HuggingFace/LLM/gemma2/README.md

@@ -4,7 +4,7 @@ In this directory, you will find examples on how you could apply IPEX-LLM INT4 o
 ## Requirements
 To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
 
-**Important: According to Gemma2's requirement, please make sure you have installed `transformers==4.43.1` and `trl` to run the example.**
+**Important: According to Gemma2's requirement, please make sure you have installed `transformers==4.43.1` and `trl<0.12.0` to run the example.**
 
 ## Example: Predict Tokens using `generate()` API
 In the example [generate.py](./generate.py), we show a basic use case for a Gemma2 model to predict the next N tokens using `generate()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
@@ -19,7 +19,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 # According to Gemma2's requirement, please make sure you are using a stable version of Transformers, 4.43.1 or newer.
 pip install "transformers>=4.43.1"
-pip install trl
+pip install "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -33,7 +33,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 # According to Gemma2's requirement, please make sure you are using a stable version of Transformers, 4.43.1 or newer.
 pip install "transformers>=4.43.1"
-pip install trl
+pip install "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/LLM/glm4/README.md

@@ -14,7 +14,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 ### 1.2 Installation on Windows
@@ -27,7 +27,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 ## 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/LLM/llama3.1/README.md

@@ -17,7 +17,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 # transformers>=4.43.1 is required for Llama3.1 with IPEX-LLM optimizations
 pip install transformers==4.43.1
-pip install trl
+pip install "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -31,7 +31,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 # transformers>=4.43.1 is required for Llama3.1 with IPEX-LLM optimizations
 pip install transformers==4.43.1
-pip install trl 
+pip install "trl<0.12.0" 
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/LLM/llama3.2/README.md

@@ -17,7 +17,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 pip install transformers==4.45.0
 pip install accelerate==0.33.0
-pip install trl
+pip install "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -31,7 +31,7 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 pip install transformers==4.45.0
 pip install accelerate==0.33.0
-pip install trl 
+pip install "trl<0.12.0" 
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-Llama3-V-2_5/README.md

@@ -15,7 +15,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install transformers==4.41.0 trl
+pip install transformers==4.41.0 "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -27,7 +27,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install transformers==4.41.0 trl
+pip install transformers==4.41.0 "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md

@@ -15,7 +15,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install transformers==4.40.0 trl
+pip install transformers==4.40.0 "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -27,7 +27,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install transformers==4.40.0 trl
+pip install transformers==4.40.0 "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/README.md

@@ -15,7 +15,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install tiktoken transformers==4.42.4 trl
+pip install tiktoken transformers==4.42.4 "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -27,7 +27,7 @@ conda activate llm
 # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
-pip install tiktoken transformers==4.42.4 trl
+pip install tiktoken transformers==4.42.4 "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables for Linux

python/llm/example/GPU/LLM-Finetuning/QLoRA/trl-example/README.md

@@ -19,7 +19,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 pip install transformers==4.36.0 datasets
 pip install peft==0.10.0
-pip install bitsandbytes scipy trl
+pip install bitsandbytes scipy "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables

python/llm/example/GPU/Lightweight-Serving/README.md

@@ -41,7 +41,7 @@ pip install gradio # for gradio web UI
 conda install -c conda-forge -y gperftools=2.10 # to enable tcmalloc
 
 # for glm-4v-9b
-pip install transformers==4.42.4 trl
+pip install transformers==4.42.4 "trl<0.12.0"
 
 # for internlm-xcomposer2-vl-7b
 pip install transformers==4.31.0

python/llm/example/GPU/PyTorch-Models/Model/glm4/README.md

@@ -16,7 +16,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 #### 1.2 Installation on Windows
@@ -29,7 +29,7 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 # install packages required for GLM-4
-pip install "tiktoken>=0.7.0" transformers==4.42.4 trl
+pip install "tiktoken>=0.7.0" transformers==4.42.4 "trl<0.12.0"
 ```
 
 ### 2. Configures OneAPI environment variables for Linux