app.py

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

hf_token = os.getenv("HF_TOKEN")
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)

model_name = "jimy26/Chatbot"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.float16,
    use_auth_token=hf_token
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=chat, inputs="text", outputs="text").launch()