app.py

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

model_name = "Hasya018/gemma-3-270m-multihopping"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

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

# ✅ Removed share=True - not needed on Hugging Face Spaces
iface.launch(server_name="0.0.0.0", server_port=7860)