Update app.py

app.py

@@ -9,7 +9,7 @@ def getLLamaresponse(input_text,no_words,blog_style):
 
     # Load model directly
 
-    model_1 = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML")
+    model_1 = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML/llama-2-7b-chat.ggmlv3.q8_0.bin")
 
     ### LLama2 model
     llm=CTransformers(model=model_1,