app.py

import gradio as gr
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "cheimaguessim/marketing-chatbot-mistral-full"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16
)

def generate(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

    outputs = model.generate(
        **inputs,
        max_new_tokens=150,
        temperature=0.7
    )

    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=generate,
    inputs="text",
    outputs="text",
    title="Marketing Chatbot"
)

iface.launch()