Update app.py

app.py

@@ -8,7 +8,7 @@ MODEL_REPO = "Kezovic/iris-q4gguf-baseline-10k"#iris-f16gguf-test" #iris-q4gguf-
 MODEL_FILE = "llama-3.2-1b-instruct.Q4_K_M.gguf"#llama-3.2-1b-instruct.F16.gguf"#Llama-3.2-1B-Instruct.Q4_K_M.gguf"#llama-3.2-1b-instruct.Q4_K_M.gguf"
 CONTEXT_WINDOW = 2048 
 MAX_NEW_TOKENS = 400  
-TEMPERATURE = 0.8     
+TEMPERATURE = 1.5     
 
 # --- Model Loading ---
 llm = None
@@ -21,7 +21,8 @@ def load_llm():
             model_path=model_path,
             n_ctx=CONTEXT_WINDOW,
             n_threads=2,
-            verbose=False
+            verbose=False,
+            min_p = 0.1
         )
         print("Model loaded successfully!")
     except Exception as e: