import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "t-tech/T-pro-it-2.0"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="T-Pro IT 2.0 Chat")
iface.launch()