app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "DeepHat/DeepHat-V1-7B"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    low_cpu_mem_usage=True
)

def chat(input_text):
    messages = [
        {"role": "system", "content": "You are a cybersecurity expert."},
        {"role": "user", "content": input_text}
    ]

    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    inputs = tokenizer(text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=120)

    return tokenizer.decode(outputs[0], skip_special_tokens=True)

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