Update app.py

app.py

@@ -1,70 +1,56 @@
 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 transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+
+MODEL_NAME = "distilgpt2"  # Modelo ligero para CPU Basic
+
+def load_model(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    gen = pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        device=-1  # CPU
+    )
+    return gen
+
+generator = load_model(MODEL_NAME)
+
+def answer(history, message):
+    if not message.strip():
+        return history, ""
+
+    context = ""
+    for user, bot in history[-6:]:
+        context += f"Usuario: {user}\nIA: {bot}\n"
+    context += f"Usuario: {message}\nIA:"
+
+    output = generator(
+        context,
+        max_new_tokens=150,
+        do_sample=True,
+        top_k=50,
+        top_p=0.9,
+        temperature=0.8
+    )[0]["generated_text"]
+
+    if "IA:" in output:
+        response = output.split("IA:")[-1].strip()
+    else:
+        response = output
+
+    history.append((message, response))
+    return history, ""
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("# 🤖 Chatbot gratuito hecho por ti")
+    chat = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Escribe un mensaje…")
+    clear_btn = gr.Button("Limpiar")
+    state = gr.State([])
 
+    msg.submit(answer, [state, msg], [chat, msg])
+    clear_btn.click(lambda: [], None, chat)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()