Python GPT2Config.get_config_dict примеры использования

Пример #1

Файл: run_generation.py Проект: rohinb/Deep-Learning

from transformers import OpenAIGPTLMHeadModel, OpenAIGPTTokenizer
from transformers import XLNetLMHeadModel, XLNetTokenizer
from transformers import TransfoXLLMHeadModel, TransfoXLTokenizer
from transformers import CTRLLMHeadModel, CTRLTokenizer
from transformers import XLMWithLMHeadModel, XLMTokenizer

logging.basicConfig(
    format='%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
    datefmt='%m/%d/%Y %H:%M:%S',
    level=logging.INFO)
logger = logging.getLogger(__name__)

MAX_LENGTH = int(10000)  # Hardcoded max length to avoid infinite loop

ALL_MODELS = sum(
    (conf for conf in (GPT2Config.get_config_dict("gpt2"),
                       OpenAIGPTConfig.get_config_dict("openai-gpt"))), ())

MODEL_CLASSES = {
    'gpt2': (GPT2LMHeadModel, GPT2Tokenizer),
    'ctrl': (CTRLLMHeadModel, CTRLTokenizer),
    'openai-gpt': (OpenAIGPTLMHeadModel, OpenAIGPTTokenizer),
    'xlnet': (XLNetLMHeadModel, XLNetTokenizer),
    'transfo-xl': (TransfoXLLMHeadModel, TransfoXLTokenizer),
    'xlm': (XLMWithLMHeadModel, XLMTokenizer),
}

# Padding text to help Transformer-XL and XLNet with short prompts as proposed by Aman Rusia
# in https://github.com/rusiaaman/XLNet-gen#methodology
# and https://medium.com/@amanrusia/xlnet-speaks-comparison-to-gpt-2-ea1a4e9ba39e
PADDING_TEXT = """ In 1991, the remains of Russian Tsar Nicholas II and his family

Пример #2

from transformers import OpenAIGPTLMHeadModel, OpenAIGPTTokenizer
from transformers import XLNetLMHeadModel, XLNetTokenizer
from transformers import TransfoXLLMHeadModel, TransfoXLTokenizer
from transformers import CTRLLMHeadModel, CTRLTokenizer
from transformers import XLMWithLMHeadModel, XLMTokenizer

logging.basicConfig(
    format='%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
    datefmt='%m/%d/%Y %H:%M:%S',
    level=logging.INFO)
logger = logging.getLogger(__name__)

MAX_LENGTH = int(10000)  # Hardcoded max length to avoid infinite loop

ALL_MODELS = sum(
    (conf for conf in (GPT2Config.get_config_dict("gpt2-medium"),
                       OpenAIGPTConfig.get_config_dict("openai-gpt"))), ())

MODEL_CLASSES = {
    'gpt2': (GPT2LMHeadModel, GPT2Tokenizer),
    'ctrl': (CTRLLMHeadModel, CTRLTokenizer),
    'openai-gpt': (OpenAIGPTLMHeadModel, OpenAIGPTTokenizer),
    'xlnet': (XLNetLMHeadModel, XLNetTokenizer),
    'transfo-xl': (TransfoXLLMHeadModel, TransfoXLTokenizer),
    'xlm': (XLMWithLMHeadModel, XLMTokenizer),
}

# Padding text to help Transformer-XL and XLNet with short prompts as proposed by Aman Rusia
# in https://github.com/rusiaaman/XLNet-gen#methodology
# and https://medium.com/@amanrusia/xlnet-speaks-comparison-to-gpt-2-ea1a4e9ba39e
PADDING_TEXT = """ In 1991, the remains of Russian Tsar Nicholas II and his family

Пример #3

    TransfoXLLMHeadModel,
    TransfoXLTokenizer,
)

logging.basicConfig(
    format='%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
    datefmt='%m/%d/%Y %H:%M:%S',
    level=logging.INFO)
logger = logging.getLogger(__name__)

MAX_LENGTH = int(10000)  # Hardcoded max length to avoid infinite loop

# ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in (GPT2Config, OpenAIGPTConfig, XLNetConfig, TransfoXLConfig)), ())
OUTPUT = os.getenv('OUTPUT')
ALL_MODELS = sum((conf
                  for conf in (GPT2Config.get_config_dict(OUTPUT),
                               OpenAIGPTConfig.get_config_dict(OUTPUT))), ())

MODEL_CLASSES = {
    'gpt2': (GPT2LMHeadModel, GPT2Tokenizer),
    'openai-gpt': (OpenAIGPTLMHeadModel, OpenAIGPTTokenizer),
    'xlnet': (XLNetLMHeadModel, XLNetTokenizer),
    'transfo-xl': (TransfoXLLMHeadModel, TransfoXLTokenizer),
}

# Padding text to help Transformer-XL and XLNet with short prompts as proposed by Aman Rusia
# in https://github.com/rusiaaman/XLNet-gen#methodology
# and https://medium.com/@amanrusia/xlnet-speaks-comparison-to-gpt-2-ea1a4e9ba39e
PADDING_TEXT = """ In 1991, the remains of Russian Tsar Nicholas II and his family
(except for Alexei and Maria) are discovered.
The voice of Nicholas's young son, Tsarevich Alexei Nikolaevich, narrates the

Пример #4

    XLNetTokenizer,
    TransfoXLLMHeadModel,
    TransfoXLTokenizer,
)

logging.basicConfig(
    format='%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
    datefmt='%m/%d/%Y %H:%M:%S',
    level=logging.INFO)
logger = logging.getLogger(__name__)

MAX_LENGTH = int(10000)  # Hardcoded max length to avoid infinite loop

#ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in (GPT2Config, OpenAIGPTConfig, XLNetConfig, TransfoXLConfig)), ())
ALL_MODELS = sum(
    (conf for conf in (GPT2Config.get_config_dict('gpt2'),
                       OpenAIGPTConfig.get_config_dict("openai-gpt"))), ())

MODEL_CLASSES = {
    'gpt2': (GPT2LMHeadModel, GPT2Tokenizer),
    'openai-gpt': (OpenAIGPTLMHeadModel, OpenAIGPTTokenizer),
    'xlnet': (XLNetLMHeadModel, XLNetTokenizer),
    'transfo-xl': (TransfoXLLMHeadModel, TransfoXLTokenizer),
}

# Padding text to help Transformer-XL and XLNet with short prompts as proposed by Aman Rusia
# in https://github.com/rusiaaman/XLNet-gen#methodology
# and https://medium.com/@amanrusia/xlnet-speaks-comparison-to-gpt-2-ea1a4e9ba39e
PADDING_TEXT = """ In 1991, the remains of Russian Tsar Nicholas II and his family
(except for Alexei and Maria) are discovered.
The voice of Nicholas's young son, Tsarevich Alexei Nikolaevich, narrates the