app.py

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

# Load model dari Hugging Face
model_id = "FaishalbhiteX/deepseek-math-finetuned"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16,device_map="auto", trust_remote_code=True)

# Fungsi chatbot
def chatbot(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio UI
iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Math Chatbot")
iface.launch()