from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

MODEL_NAME = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto"
)

model.eval()