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

base_model_id = "HooshvareLab/gpt2-fa"
lora_model_id = "SEDNA-AI/sedna-gpt2-lora"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(base_model, lora_model_id)

def chat(user_input):
    prompt = f"سوال: {user_input}\nپاسخ:"
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        temperature=0.7,
        do_sample=True
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.split("پاسخ:")[-1].strip()

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="SEDNA Chatbot")
iface.launch()