app.py

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

model_id = "microsoft/Magma-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    trust_remote_code=True
)

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

interface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs="text",
    title="Magma-8B Text Generator"
)

interface.launch(share=False, enable_queue=True)