app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "1c1/7cpc"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    load_in_8bit=True,
    torch_dtype=torch.float16,
    low_cpu_mem_usage=True
)