try to improve the inference

app.py

@@ -14,18 +14,10 @@ model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="cpu",
     torch_dtype=torch.float32,
-    low_cpu_mem_usage=True,
-    offload_folder="offload",
-    offload_state_dict=True
-)
-
-print("⚙️ Quantification du modèle pour optimisation CPU...")
-model = torch.quantization.quantize_dynamic(
-    model,
-    {torch.nn.Linear},
-    dtype=torch.qint8
+    low_cpu_mem_usage=True
 )
 
+print("✅ Modèle chargé avec optimisations CPU")
 model.eval()
 
 SYSTEM_PROMPT = "You are a helpful AI assistant based on Meta's Llama-3.2-3B model, fine-tuned on a code dataset."