加载huggingface预训练的变压器模型似乎需要您将模型保存在本地(如此处所述),这样您只需将本地路径传递给模型和配置即可:
model = PreTrainedModel.from_pretrained('path/to/model', local_files_only=True)
模型存储在S3上可以实现吗?
回答我自己的问题...(显然鼓励)
我使用瞬态文件(
NamedTemporaryFile
)实现了这一点,它可以达到目的。我希望找到一个内存中的解决方案(即将 BytesIO
直接传递到 from_pretrained
),但这需要对 transformers
代码库进行补丁
import boto3
import json
from contextlib import contextmanager
from io import BytesIO
from tempfile import NamedTemporaryFile
from transformers import PretrainedConfig, PreTrainedModel
@contextmanager
def s3_fileobj(bucket, key):
"""
Yields a file object from the filename at {bucket}/{key}
Args:
bucket (str): Name of the S3 bucket where you model is stored
key (str): Relative path from the base of your bucket, including the filename and extension of the object to be retrieved.
"""
s3 = boto3.client("s3")
obj = s3.get_object(Bucket=bucket, Key=key)
yield BytesIO(obj["Body"].read())
def load_model(bucket, path_to_model, model_name='pytorch_model'):
"""
Load a model at the given S3 path. It is assumed that your model is stored at the key:
'{path_to_model}/{model_name}.bin'
and that a config has also been generated at the same path named:
f'{path_to_model}/config.json'
"""
tempfile = NamedTemporaryFile()
with s3_fileobj(bucket, f'{path_to_model}/{model_name}.bin') as f:
tempfile.write(f.read())
with s3_fileobj(bucket, f'{path_to_model}/config.json') as f:
dict_data = json.load(f)
config = PretrainedConfig.from_dict(dict_data)
model = PreTrainedModel.from_pretrained(tempfile.name, config=config)
return model
model = load_model('my_bucket', 'path/to/model')
也可以对模型目录执行类似的操作:
def load_project_processing_models_from_s3():
s3_client = get_s3_client()
result = s3_client.list_objects(
Bucket=secret_vault.AWS_S3_MODELS_DIRECTORY,
Prefix=secret_vault.AWS_S3_DOC_PARSER_MODEL_DIR,
)
# Create a temporary directory
temp_dir = tempfile.mkdtemp()
keys = [obj["Key"] for obj in result.get("Contents", [])]
for key in keys:
file_path = os.path.join(temp_dir, os.path.basename(key))
with open(file_path, "wb") as file:
file_data = s3_client.get_object(
Bucket=secret_vault.AWS_S3_MODELS_DIRECTORY, Key=key
)
file.write(file_data["Body"].read())
# Load the Hugging Face model from the temporary directory
model = AutoModel.from_pretrained(temp_dir)
# Clean up the temporary directory
shutil.rmtree(temp_dir)
return model