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


base_model = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
adapter_model = "Sanjay002/falcon-7b-mental-health-finetuned"

device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    device_map=None,  # Don't map to GPU
    torch_dtype=torch.float32 if device == "cpu" else torch.bfloat16,
    trust_remote_code=True
)

model = PeftModel.from_pretrained(model, adapter_model)
model.to(device)
model.eval()

def chat(message):
    inputs = tokenizer(message, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_new_tokens=150, do_sample=True, temperature=0.7)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

gr.Interface(fn=chat, inputs="text", outputs="text", title="🧠 Mental Health Chatbot").queue().launch()