Update app.py

app.py

@@ -41,11 +41,15 @@ def load_model():
         repo_id="Mykes/med_phi3-mini-4k-GGUF",
         filename="*Q4_K_M.gguf",
         verbose=False,
-        n_ctx=1024,
-        n_batch=512,
-        n_threads=8,
-        use_mlock=True,
+        n_ctx=256,  # Reduced context window
+        n_batch=8,  # Smaller batch size
+        n_threads=2,  # Adjust based on your CPU cores
         use_mmap=True,
+        # n_ctx=1024,
+        # n_batch=512,
+        # n_threads=8,
+        # use_mlock=True,
+        # use_mmap=True,
     )
 
 llm = load_model()