Update README.md

README.md

@@ -61,7 +61,7 @@ temperature = 0.8
 
 The following provides demo code illustrating how to generate based on text and multimodal inputs.
 
-> **Please use transformers>=4.53.0 to ensure the model works normally.**
+> **Please use transformers>=4.55.2 to ensure the model works normally.**
 
 #### Text input
 
@@ -118,7 +118,7 @@ print(decoded_output)
 
 #### Video input
 
-Please ensure that the decord video decoding library is installed via `pip install decord`.
+Please ensure that the decord video decoding library is installed via `pip install decord`. To avoid OOM, please at least use 2 GPUS.
 
 ```python
 from transformers import AutoProcessor, AutoModelForCausalLM