Create app.py

app.py

@@ -0,0 +1,45 @@
+import os
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+MODEL_ID = "mradermacher/sk2decompile-struct-6.7b-GGUF"
+
+def get_client(hf_token):
+    token = getattr(hf_token, "token", None) or os.getenv("HF_TOKEN")
+    return InferenceClient(model=MODEL_ID, token=token)
+
+def respond(message, history, system_message, max_tokens, temperature, top_p, hf_token: gr.OAuthToken):
+    try:
+        client = get_client(hf_token)
+        messages = [{"role": "system", "content": system_message}]
+        messages += history
+        messages.append({"role": "user", "content": message})
+        response = ""
+        for chunk in client.chat_completion(messages=messages, max_tokens=max_tokens, stream=True,
+                                            temperature=temperature, top_p=top_p):
+            token = getattr(chunk.choices[0].delta, "content", "") if hasattr(chunk.choices[0], "delta") else ""
+            response += token
+            yield response
+    except Exception as e:
+        yield f"❌ Erro: {e}"
+
+chatbot = gr.ChatInterface(
+    respond,
+    type="messages",
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.LoginButton(),
+    ],
+)
+
+demo = gr.Blocks()
+with demo:
+    with gr.Sidebar():
+        gr.Markdown("Login com Hugging Face para usar o modelo protegido.")
+    chatbot.render()
+
+if __name__ == "__main__":
+    demo.launch()