Update app.py

app.py

@@ -1,64 +1,65 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+# Configuración del modelo
+MODEL_NAME = "microsoft/phi-2"  # Modelo ligero y eficiente
 
+# Cargar modelo y tokenizer
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+def generate_response(message, history, system_prompt="Eres un asistente útil llamado Gerardo."):
+    # Formatear el historial de chat
+    messages = [{"role": "system", "content": system_prompt}]
+    for user_msg, bot_msg in history:
+        messages.extend([
+            {"role": "user", "content": user_msg},
+            {"role": "assistant", "content": bot_msg}
+        ])
     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,
-    ):
-        token = message.choices[0].delta.content
+    # Generar respuesta con streaming
+    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
+    
+    Thread(
+        target=model.generate,
+        kwargs=dict(
+            inputs,
+            streamer=streamer,
+            max_new_tokens=512,
+            temperature=0.7,
+            do_sample=True
+        )
+    ).start()
 
+    # Retornar la respuesta progresivamente
+    response = ""
+    for token in streamer:
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Interfaz con Gradio
 demo = gr.ChatInterface(
-    respond,
+    fn=generate_response,
+    title="🤖 Chatbot Gerardo",
+    description="Un asistente IA creado por Gerardo. ¡Pregúntame lo que quieras!",
+    examples=["Hola", "¿Cómo funciona la inteligencia artificial?"],
     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)",
-        ),
+        gr.Textbox(
+            "Eres un asistente útil llamado Gerardo.",
+            label="Personalidad del bot"
+        )
     ],
+    theme="soft"
 )
 
-
 if __name__ == "__main__":
     demo.launch()
+