Update app.py

app.py

@@ -14,12 +14,13 @@ logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
 
 def configure_llama_model():
-    model_url = 'https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf'
+    
+    model_url = 'https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF/resolve/main/mistral-7b-v0.1.Q4_K_M.gguf'
     llm = LlamaCPP(
         model_url=model_url,
         temperature=0.3,
-        max_new_tokens=68,
-        context_window=1000,
+        max_new_tokens=256,
+        context_window=3900,
         model_kwargs={"n_gpu_layers": 1},
         messages_to_prompt=messages_to_prompt,
         completion_to_prompt=completion_to_prompt,