Transformers2.0让你三行代码调用语言模型，兼容TF2.0和PyTorch

import torch
from transformers import *

#Transformers has a unified API
#for 8 transformer architectures and 30 pretrained weights.
#Model          | Tokenizer          | Pretrained weights shortcut

MODELS = [(BertModel,       BertTokenizer,       'bert-base-uncased'),
          (OpenAIGPTModel,  OpenAIGPTTokenizer,  'openai-gpt'),
          (GPT2Model,       GPT2Tokenizer,       'gpt2'),
          (TransfoXLModel,  TransfoXLTokenizer,  'transfo-xl-wt103'),
          (XLNetModel,      XLNetTokenizer,      'xlnet-base-cased'),
          (XLMModel,        XLMTokenizer,        'xlm-mlm-enfr-1024'),
          (DistilBertModel, DistilBertTokenizer, 'distilbert-base-uncased'),
          (RobertaModel,    RobertaTokenizer,    'roberta-base')]

#To use TensorFlow 2.0 versions of the models, simply prefix the class names with 'TF', e.g. TFRobertaModel is the TF 2.0 counterpart of the PyTorch model RobertaModel
#Let's encode some text in a sequence of hidden-states using each model:
for model_class, tokenizer_class, pretrained_weights in MODELS:
    # Load pretrained model/tokenizer
    tokenizer = tokenizer_class.from_pretrained(pretrained_weights)
    model = model_class.from_pretrained(pretrained_weights)

    # Encode text
    input_ids = torch.tensor([tokenizer.encode("Here is some text to encode", add_special_tokens=True)])  # Add special tokens takes care of adding [CLS], [SEP], <s>... tokens in the right way for each model.
    with torch.no_grad():
        last_hidden_states = model(input_ids)[0]  # Models outputs are now tuples

#Each architecture is provided with several class for fine-tuning on down-stream tasks, e.g.
BERT_MODEL_CLASSES = [BertModel, BertForPreTraining, BertForMaskedLM, BertForNextSentencePrediction,
                      BertForSequenceClassification, BertForMultipleChoice, BertForTokenClassification,
                      BertForQuestionAnswering]

#All the classes for an architecture can be initiated from pretrained weights for this architecture
#Note that additional weights added for fine-tuning are only initialized
#and need to be trained on the down-stream tasktokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
for model_class in BERT_MODEL_CLASSES:
    # Load pretrained model/tokenizer
    model = model_class.from_pretrained('bert-base-uncased')

#Models can return full list of hidden-states & attentions weights at each layer
model = model_class.from_pretrained(pretrained_weights,
                                    output_hidden_states=True,
                                    output_attentions=True)
input_ids = torch.tensor([tokenizer.encode("Let's see all hidden-states and attentions on this text")])
all_hidden_states, all_attentions = model(input_ids)[-2:]

#Models are compatible with Torchscript
model = model_class.from_pretrained(pretrained_weights, torchscript=True)
traced_model = torch.jit.trace(model, (input_ids,))

#Simple serialization for models and tokenizers
model.save_pretrained('./directory/to/save/')  # save
model = model_class.from_pretrained('./directory/to/save/')  # re-load
tokenizer.save_pretrained('./directory/to/save/')  # save
tokenizer = tokenizer_class.from_pretrained('./directory/to/save/')  # re-load

#SOTA examples for GLUE, SQUAD, text generation...

import tensorflow as tf
import tensorflow_datasets
from transformers import *

#Load dataset, tokenizer, model from pretrained model/vocabulary
tokenizer = BertTokenizer.from_pretrained('bert-base-cased')
model = TFBertForSequenceClassification.from_pretrained('bert-base-cased')
data = tensorflow_datasets.load('glue/mrpc')

#Prepare dataset for GLUE as a tf.data.Dataset instance
train_dataset = glue_convert_examples_to_features(data['train'], tokenizer, max_length=128, task='mrpc')
valid_dataset = glue_convert_examples_to_features(data['validation'], tokenizer, max_length=128, task='mrpc')
train_dataset = train_dataset.shuffle(100).batch(32).repeat(2)
valid_dataset = valid_dataset.batch(64)

#Prepare training: Compile tf.keras model with optimizer, loss and learning rate schedule 
optimizer = tf.keras.optimizers.Adam(learning_rate=3e-5, epsilon=1e-08, clipnorm=1.0)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
model.compile(optimizer=optimizer, loss=loss, metrics=[metric])

#Train and evaluate using tf.keras.Model.fit()
history = model.fit(train_dataset, epochs=2, steps_per_epoch=115,
                    validation_data=valid_dataset, validation_steps=7)

#Load the TensorFlow model in PyTorch for inspection
model.save_pretrained('./save/')
pytorch_model = BertForSequenceClassification.from_pretrained('./save/', from_tf=True)

#Quickly test a few predictions - MRPC is a paraphrasing task, let's see if our model learned the task
sentence_0 = "This research was consistent with his findings.“
sentence_1 = "His findings were compatible with this research.“
sentence_2 = "His findings were not compatible with this research.“
inputs_1 = tokenizer.encode_plus(sentence_0, sentence_1, add_special_tokens=True, return_tensors='pt')
inputs_2 = tokenizer.encode_plus(sentence_0, sentence_2, add_special_tokens=True, return_tensors='pt')

pred_1 = pytorch_model(*inputs_1)[0].argmax().item()
pred_2 = pytorch_model(*inputs_2)[0].argmax().item()
print("sentence_1 is", "a paraphrase" if pred_1 else "not a paraphrase", "of sentence_0")
print("sentence_2 is", "a paraphrase" if pred_2 else "not a paraphrase", "of sentence_0")

pip install -r ./examples/requirements.txt

export GLUE_DIR=/path/to/glue
export TASK_NAME=MRPC

python ./examples/run_glue.py \
 --model_type bert \
 --model_name_or_path bert-base-uncased \
 --task_name $TASK_NAME \
 --do_train \
 --do_eval \
 --do_lower_case \
 --data_dir $GLUE_DIR/$TASK_NAME \
 --max_seq_length 128 \
 --per_gpu_eval_batch_size=8 \
 --per_gpu_train_batch_size=8 \
 --learning_rate 2e-5 \
 --num_train_epochs 3.0 \
 --output_dir /tmp/$TASK_NAME/

python -m torch.distributed.launch --nproc_per_node=8 ./examples/run_squad.py \
 --model_type bert \
 --model_name_or_path bert-large-uncased-whole-word-masking \
 --do_train \
 --do_eval \
 --do_lower_case \
 --train_file $SQUAD_DIR/train-v1.1.json \
 --predict_file $SQUAD_DIR/dev-v1.1.json \
 --learning_rate 3e-5 \
 --num_train_epochs 2 \
 --max_seq_length 384 \
 --doc_stride 128 \
 --output_dir ../models/wwm_uncased_finetuned_squad/ \
 --per_gpu_eval_batch_size=3 \
 --per_gpu_train_batch_size=3 \

python ./examples/run_generation.py \
 --model_type=gpt2 \
 --length=20 \
 --model_name_or_path=gpt2 \

pip install transformers