Update app.py

app.py

@@ -1,26 +1,19 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-import torch
 import gradio as gr
+import requests
 
-model_id = "NousResearch/zephyr-1.3b"
+API_URL = "https://api-inference.huggingface.co/models/TheBloke/MythoMax-L2-13B-GGUF"
+headers = {"Authorization": "Bearer TU_TOKEN_DE_HUGGINGFACE"}
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.float32
-)
+def responder(prompt):
+    payload = {
+        "inputs": prompt,
+        "parameters": {"max_new_tokens": 200}
+    }
+    response = requests.post(API_URL, headers=headers, json=payload)
+    try:
+        return response.json()[0]["generated_text"]
+    except:
+        return "Error en la respuesta del modelo."
 
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-def generate_text(prompt):
-    output = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)
-    return output[0]["generated_text"]
-
-demo = gr.Interface(
-    fn=generate_text,
-    inputs=gr.Textbox(lines=4, placeholder="Escribe algo..."),
-    outputs="text",
-    title="Generador de texto - Zephyr 1.3B (CPU compatible)"
-)
-
-demo.launch()
+iface = gr.Interface(fn=responder, inputs="text", outputs="text", title="MythoMax Chatbot")
+iface.launch()