Upload README.md

change the requirement for the version of `transformers`.

README.md

@@ -52,7 +52,7 @@ We will provide a detailed guide later on how to modify your `modeling_xxx.py` f
 ### 2.2 Quick Start
 
 #### 2.2.1 Environment Setup
-You need to install `transformers>=4.53`, and we recommend using `lm_eval>=0.4.9` for running evaluations. We suggest managing your Python environment with `conda` for better dependency control.
+You need to install `transformers>=4.53.0,<4.54.0`, and we recommend using `lm_eval>=0.4.9` for running evaluations. We suggest managing your Python environment with `conda` for better dependency control.
 
 ```bash
 conda create -n sepcache python=3.10
@@ -64,7 +64,7 @@ pip install lm_eval==0.4.9
 You can use `SepCache` by specifying `custom_generate="transformers-community/sep_cache"` or `custom_generate="Gausson/sep_cache"` when calling the `generate` function. In our demo, we have already prepared sample monkey patching for the `Llama 3 series` models and provided some common parameters for initializing `SepCache`.
 
 ```python
-# requires `transformers>=4.53.0`
+# requires `transformers>=4.53.0,<4.54.0`
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Preparing model, tokenizer, and model inputs