generate_samples_gpt2.py

# coding=utf-8
# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
#
# 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.

"""Sample Generate GPT2"""

from megatron import get_args
from megatron import get_tokenizer
from megatron import print_rank_0
from megatron.checkpointing import load_checkpoint
from megatron.initialize import initialize_megatron
from megatron.model import GPT2Model
from megatron.training import get_model
from megatron.text_generation_utils import generate_and_write_samples_unconditional
from megatron.text_generation_utils import generate_samples_input_from_file
from megatron.text_generation_utils import generate_samples_interactive


def model_provider():
    """Build the model."""

    print_rank_0('building GPT2 model ...')
    model = GPT2Model(num_tokentypes=0, parallel_output=False)

    return model


def add_text_generate_args(parser):
    """Text generation arguments."""
    group = parser.add_argument_group(title='text generation')

    group.add_argument("--temperature", type=float, default=1.0,
                       help='Sampling temperature.')
    group.add_argument("--greedy", action='store_true', default=False,
                       help='Use greedy sampling.')
    group.add_argument("--top_p", type=float, default=0.0,
                       help='Top p sampling.')
    group.add_argument("--top_k", type=int, default=0,
                       help='Top k sampling.')
    group.add_argument("--out-seq-length", type=int, default=1024,
                       help='Size of the output generated text.')
    group.add_argument("--sample-input-file", type=str, default=None,
                       help='Get input from file instead of interactive mode, '
                       'each line is an input.')
    group.add_argument("--sample-output-file", type=str, default=None,
                       help='Output file got from --sample-input-file')
    group.add_argument("--num-samples", type=int, default=0,
                       help='Number of samples to generate unconditionally, '
                       'defaults to 0 and interactive conditional sampling')
    group.add_argument("--genfile", type=str,
                       help='Output file when generating unconditionally')
    group.add_argument("--recompute", action='store_true',
                       help='During generation recompute all attention '
                       'instead of using previously computed keys/values.')

    return parser


def main():
    """Main program."""

    initialize_megatron(extra_args_provider=add_text_generate_args,
                        args_defaults={'tokenizer_type': 'GPT2BPETokenizer'})

    # Set up model and load checkpoint.
    model = get_model(model_provider)
    args = get_args()
    if args.load is not None:
        _ = load_checkpoint(model, None, None)

    # Generate samples.
    if args.num_samples == 0:
        args.batch_size = 1
        if args.sample_input_file != "":
            generate_samples_input_from_file(model)
        else:
            generate_samples_interactive(model)
    else:
        generate_and_write_samples_unconditional(model)


if __name__ == "__main__":

    main()