Create app.py

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+from llama_cpp import Llama
+
+# Charger le modèle GGUF (Q8_0)
+llm = Llama(
+    model_path="model/gptq_model.gguf",
+    n_threads=1,
+    n_ctx=2048,
+    n_batch=64,
+    use_mlock=True
+)
+
+def generate(prompt):
+    output = llm(prompt, max_tokens=200, stop=["</s>"], echo=False)
+    return output["choices"][0]["text"]
+
+# UI Gradio
+iface = gr.Interface(fn=generate, 
+                     inputs=gr.Textbox(lines=5, label="Prompt"),
+                     outputs=gr.Textbox(label="Réponse"),
+                     title="WizzGPT - CPU Demo")
+
+iface.launch()