Update app.py

app.py

@@ -1,89 +1,29 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+modelo = "tu_usuario/mi-ia-chatbot"  # tu modelo subido
+tokenizer = AutoTokenizer.from_pretrained(modelo)
+model = AutoModelForCausalLM.from_pretrained(modelo)
 
-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")
+def responder(mensaje, historial):
+    if historial is None:
+        historial = []
 
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
-def chat(prompt, max_length=200):
-    # Convertimos el prompt en tensores para el modelo
-    inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
-    
-    # Generamos la respuesta del modelo
-    outputs = model.generate(
-        inputs,
-        max_length=max_length,
+    entradas = tokenizer.encode(mensaje + tokenizer.eos_token, return_tensors="pt")
+    salida = model.generate(
+        entradas,
+        max_length=150,
         pad_token_id=tokenizer.eos_token_id,
-        do_sample=True,
-        top_p=0.9,
-        temperature=0.7
+        temperature=0.7,
+        top_p=0.9
     )
-    
-    # ⚡ Aquí ponemos el código para quitar la columna de tokens
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    # Devolvemos solo la respuesta en texto plano
-    return response[len(prompt):].strip()
+    respuesta = tokenizer.decode(salida[:, entradas.shape[-1]:][0], skip_special_tokens=True)
+    historial.append((mensaje, respuesta))
+    return historial, historial
+
+demo = gr.Blocks()
+with demo:
+    chat = gr.Chatbot()
+    entrada = gr.Textbox()
+    entrada.submit(responder, [entrada, chat], [chat, chat])
+demo.launch()