Update app.py

app.py

@@ -1,28 +1,26 @@
-import gradio as gr
-import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+import gradio as gr
 
-model_id = "HuggingFaceH4/zephyr-7b-beta"
+model_id = "NousResearch/zephyr-1.3b"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto"
+    torch_dtype=torch.float32
 )
 
-pipe = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    max_new_tokens=200,
-    do_sample=True,
-    temperature=0.7,
-    top_p=0.9,
-)
+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"]
 
-def responder(prompt):
-    respuesta = pipe(prompt)[0]["generated_text"]
-    return respuesta.split(prompt)[-1].strip()
+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)"
+)
 
-gr.Interface(fn=responder, inputs="text", outputs="text", title="Bot de Texto").launch()
+demo.launch()