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

model_id = "ramyaa1113/gemma2b-webxr-showroom-v2"

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

def generate(prompt):

    inputs = tokenizer(prompt, return_tensors="pt")

    outputs = model.generate(
        **inputs,
        max_new_tokens=150
    )

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

demo = gr.Interface(
    fn=generate,
    inputs="text",
    outputs="text"
)

demo.launch()