app.py

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

# Load Model & Tokenizer
MODEL_NAME = "tezodipta/MindEase-Assistant-v0.1"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")

# Function to Generate Response
def generate_response(prompt):
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    output = model.generate(input_ids, max_length=200, temperature=0.7, do_sample=True, top_p=0.9)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Gradio UI
interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="MindEase AI Assistant",
    description="Chat with a Mental Health AI Assistant",
)

interface.launch(server_name="0.0.0.0", server_port=7860, share=True)