Update app.py

app.py

@@ -96,13 +96,21 @@ embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-b
 
 # Initialize the models
 def initialize_phi_model():
+    # model = AutoModelForCausalLM.from_pretrained(
+    #     "microsoft/Phi-3.5-mini-instruct",
+    #     device_map="cuda",
+    #     torch_dtype="auto",
+    #     trust_remote_code=True,
+    # )
     model = AutoModelForCausalLM.from_pretrained(
-        "microsoft/Phi-3.5-mini-instruct",
+        "microsoft/Phi-3.5-MoE-instruct",
         device_map="cuda",
         torch_dtype="auto",
         trust_remote_code=True,
     )
-    tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
+    # tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
+    tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-MoE-instruct")
+    
     return pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def initialize_gpt_model():
@@ -660,7 +668,7 @@ def generate_answer(message, choice, retrieval_mode, selected_model):
 
                 response = selected_model(prompt, **{
                     "max_new_tokens": 300,
-                    "return_full_text": True,
+                    "return_full_text": False,
                     "temperature": 0.0,
                     "do_sample": False,
                 })