Update app.py

app.py

@@ -5,7 +5,7 @@ configObj = ctransformers.Config(stop=["\n", 'User'])
 config = ctransformers.AutoConfig(config=configObj, model_type='llama')
 config.config.stop = ["\n"]
 
-llm = ctransformers.AutoModelForCausalLM.from_pretrained('ML610/llama-2-7b-chat-ggml', config=config)
+llm = ctransformers.AutoModelForCausalLM.from_pretrained('ML610/llama-2-7b-chat-ggml/llama-2-7b-chat.ggmlv3.q4_1.bin', config=config)
 
 def complete(prompt, stop=["User", "Assistant"]):
   tokens = llm.tokenize(prompt)