app.py

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

model_id = "Datangtang/GGUF_New_1B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu")

def chat_fn(message):
    inputs = tokenizer(message, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=150)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

demo = gr.Interface(fn=chat_fn, inputs="text", outputs="text", title="My Finetuned LLM Chat")

demo.launch()