app.py

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

MODEL_NAME = "aijadugar/ft_slm_model"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    torch_dtype=torch.float16,
    device_map=None
)
model = model.to("cpu")

def generate_response(user_input):
    inputs = tokenizer(user_input, return_tensors="pt").to(model.device)

    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        temperature=0.7,
        top_p=0.9,
    )

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

demo = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(label="Enter your query"),
    outputs=gr.Textbox(label="Model response"),
    title="SLM Technical Support Bot",
)

demo.launch()