Update app.py

app.py

@@ -7,9 +7,9 @@ title = "🤖AI ChatBot"
 description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
 examples = [["How are you?"]]
 
-tokenizer = AutoTokenizer.from_pretrained("stvlynn/Gemma-2-2b-Chinese-it")
-model = AutoModelForCausalLM.from_pretrained("stvlynn/Gemma-2-2b-Chinese-it", torch_dtype=torch.float16)
-
+tokenizer = AutoTokenizer.from_pretrained("models/google/gemma-2-2b-it")
+model = AutoModelForCausalLM.from_pretrained("models/google/gemma-2-2b-it", torch_dtype=torch.float16)
+#stvlynn/Gemma-2-2b-Chinese-it
 #tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
 #model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 #The model was loaded with use_flash_attention_2=True, which is deprecated and may be removed in a future release. Please use `attn_implementation="flash_attention_2"` instead.