Page MenuHomec4science
Files F60592099

convert_funnel_original_tf_checkpoint_to_pytorch.py
No OneTemporary
Actions

File Metadata

Created
Wed, May 1, 08:09

convert_funnel_original_tf_checkpoint_to_pytorch.py
View Options

# coding=utf-8
# Copyright 2020 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Convert Funnel checkpoint."""
import argparse
import torch
from transformers import FunnelBaseModel, FunnelConfig, FunnelModel, load_tf_weights_in_funnel
from transformers.utils import logging
logging.set_verbosity_info()
def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, config_file, pytorch_dump_path, base_model):
# Initialise PyTorch model
config = FunnelConfig.from_json_file(config_file)
print("Building PyTorch model from configuration: {}".format(str(config)))
model = FunnelBaseModel(config) if base_model else FunnelModel(config)
# Load weights from tf checkpoint
load_tf_weights_in_funnel(model, config, tf_checkpoint_path)
# Save pytorch-model
print("Save PyTorch model to {}".format(pytorch_dump_path))
torch.save(model.state_dict(), pytorch_dump_path)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument(
"--tf_checkpoint_path", default=None, type=str, required=True, help="Path to the TensorFlow checkpoint path."
)
parser.add_argument(
"--config_file",
default=None,
type=str,
required=True,
help="The config json file corresponding to the pre-trained model. \n"
"This specifies the model architecture.",
)
parser.add_argument(
"--pytorch_dump_path", default=None, type=str, required=True, help="Path to the output PyTorch model."
)
parser.add_argument(
"--base_model", action="store_true", help="Whether you want just the base model (no decoder) or not."
)
args = parser.parse_args()
convert_tf_checkpoint_to_pytorch(
args.tf_checkpoint_path, args.config_file, args.pytorch_dump_path, args.base_model
)

Event Timeline

c4science · Help