Upload folder using huggingface_hub

app.py

@@ -11,8 +11,10 @@ model_path = "model.gguf"
 print(f"Loading model from {model_path}...")
 llm = Llama(
     model_path=model_path,
-    n_ctx=4096,
-    n_threads=4,
+    n_ctx=1024,      # Drastically reduced context size (saves memory/time on CPU)
+    n_threads=8,     # Maximize all available vCPUs
+    n_threads_batch=8, # Speed up prompt processing
+    n_batch=256,     # Optimize batch size for prompt evaluation
     verbose=False
 )