GemmaForCausalLM import error fix

adding the GemmaForCausalLM as import for transformers as the instructions to use the provided code do not describe how to import gemma otherwise.

README.md

@@ -46,8 +46,7 @@ Octopus-V2-2B, an advanced open-source language model with 2 billion parameters,
 
 You can run the model on a GPU using the following code. 
 ```python
-from gemma.modeling_gemma import GemmaForCausalLM
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, GemmaForCausalLM
 import torch
 import time