Update app.py

app.py

@@ -92,21 +92,21 @@ def getLLMModel(LLMID):
     if LLMID == 1:
         llm = Replicate(
             model="a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
-            model_kwargs={"temperature": 0.2, "max_length": 2500})
+            model_kwargs={"temperature": 0.2,"max_new_tokens":2500})
         print("LLAMA2 13B LLM Selected")
     elif LLMID == 2:
         llm = Replicate(
             model="replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf",
-            model_kwargs={"temperature": 0.2, "max_length": 2500})
+            model_kwargs={"temperature": 0.2,"max_new_tokens":2500})
         print("LLAMA2 7B LLM Selected")
     elif LLMID == 3:
         llm = Replicate(model="meta/llama-2-7b-chat:8e6975e5ed6174911a6ff3d60540dfd4844201974602551e10e9e87ab143d81e",
-                        model_kwargs={"temperature": 0.2, "max_length": 10000})
+                        model_kwargs={"temperature": 0.2,"max_new_tokens":2500})
         print("LLAMA2 7B Chat LLM Selected")
     elif LLMID == 4:
         llm = Replicate(
             model="a16z-infra/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70",
-            model_kwargs={"temperature": 0.2, "max_length": 10000})
+            model_kwargs={"temperature": 0.2,"max_new_tokens":2500})
         print("Mistral AI LLM Selected")
     else:
         llm = OpenAI(temperature=0.0)