Update app.py

app.py

@@ -1,70 +1,45 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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)",
-        ),
-    ],
+from llama_cpp import Llama
+import os
+
+# Baixe o GGUF e suba pro Space (via Files > Upload files)
+MODEL_PATH = "DeepHat-V1-7B.Q4_K_M.gguf"  # Coloque o arquivo aqui
+
+# Carregue o modelo (ajuste n_ctx pra contexto, n_threads pra CPU cores)
+llm = Llama(
+    model_path=MODEL_PATH,
+    n_ctx=2048,  # Contexto pra prompts longos (ex.: tutoriais hacking)
+    n_threads=4,  # Use mais se sua máquina tiver
+    verbose=False
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+def generate_response(prompt, max_tokens=500):
+    # Prompt template pro DeepHat (ajuste se precisar)
+    full_prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+    
+    output = llm(
+        full_prompt,
+        max_tokens=max_tokens,
+        temperature=0.7,
+        top_p=0.9,
+        stop=["<|im_end|>", "</s>"]
+    )
+    return output['choices'][0]['text'].strip()
+
+# Interface Gradio simples pra chat
+with gr.Blocks(title="DeepHat Uncensored Chat") as demo:
+    gr.Markdown("# DeepHat - IA Uncensored pra Cibersegurança & Hacking Ético")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Pergunte sobre hacking WiFi, pentest ou censura...")
+    clear = gr.Button("Clear")
+
+    def respond(message, chat_history):
+        bot_message = generate_response(message)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()