Update app.py

app.py

@@ -1,23 +1,28 @@
 import gradio as gr
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-from diffusers import StableDiffusionPipeline
-from huggingface_hub import login
-import os
-from PIL import Image
-import io
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-login(token=os.environ["HF_TOKEN"])
+model_id = "HuggingFaceH4/zephyr-7b-beta"
 
-model_id = "mistralai/Mistral-7B-Instruct-v0.1"  # Requiere acceso
-tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=True)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16, use_auth_token=True)
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
 
-def chat(user_input):
-    prompt = f"""<s>[INST] {user_input.strip()} [/INST]"""
-    output = pipe(prompt, max_new_tokens=200, temperature=0.7, do_sample=True)[0]["generated_text"]
-    response = output.split("[/INST]")[-1].strip()
-    return response
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=200,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+)
 
-gr.Interface(fn=chat, inputs="text", outputs="text", title="MyBot - Texto").launch()
+def responder(prompt):
+    respuesta = pipe(prompt)[0]["generated_text"]
+    return respuesta.split(prompt)[-1].strip()
+
+gr.Interface(fn=responder, inputs="text", outputs="text", title="Bot de Texto").launch()