报错信息 

/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py:1006: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.
  warnings.warn(
/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:479: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.
  warnings.warn(
Traceback (most recent call last):
  File "/colab/./1.py", line 26, in <module>
    model = transformers.AutoModelForCausalLM.from_pretrained(
  File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py", line 563, in from_pretrained
    return model_class.from_pretrained(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 2487, in from_pretrained
    raise ImportError(
ImportError: Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or pip install bitsandbytes`

最终执行如下命令解决

pip3 uninstall  transformers --yes
pip install  transformers==4.30.0

再次执行就报错了

from torch import cuda, bfloat16
import transformers

model_id = 'meta-llama/Llama-2-7b-chat-hf'

device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'

# set quantization configuration to load large model with less GPU memory
# this requires the `bitsandbytes` library
bnb_config = transformers.BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type='nf4',
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=bfloat16
)

# begin initializing HF items, you need an access token
hf_auth = 'xxxxxxxxx-dddd---sdfsdfsdff'
model_config = transformers.AutoConfig.from_pretrained(
    model_id,
    use_auth_token=hf_auth
)

model = transformers.AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    config=model_config,
    quantization_config=bnb_config,
    device_map='auto',
    use_auth_token=hf_auth
)

# enable evaluation mode to allow model inference
model.eval()

print(f"Model loaded on {device}")

执行结果