app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "TheCarBun/GPT-2-fine-tuned-mental-health"
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

def chatbot_response(text):
    inputs = tokenizer(text, return_tensors="pt").to("cuda")
    output = model.generate(**inputs, max_new_tokens=50)
    return tokenizer.decode(output[0], skip_special_tokens=True)

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