Contoh kod penalaan halus Huggingface BART: Set data WMT16 untuk melatih teg baharu untuk terjemahan

from tokenizers import normalizers, pre_tokenizers, Tokenizer, models, trainers
 
 # Build a tokenizer
 bpe_tokenizer = Tokenizer(models.BPE())
 bpe_tokenizer.normalizer = normalizers.Lowercase()
 bpe_tokenizer.pre_tokenizer = pre_tokenizers.Whitespace()
 
 trainer = trainers.BpeTrainer(
 vocab_size=50265,
 special_tokens=["<s>", "<pad>", "</s>", "<unk>", "<mask>"],
 initial_alphabet=pre_tokenizers.ByteLevel.alphabet(),
 )

def batch_iterator():
 batch_length = 1000
 for i in range(0, len(train), batch_length):
 yield train[i : i + batch_length]["ro"]
 
 bpe_tokenizer.train_from_iterator( batch_iterator(), length=len(train), trainer=trainer )
 
 bpe_tokenizer.save("./ro_tokenizer.json")

from transformers import AutoTokenizer, PreTrainedTokenizerFast
 
 en_tokenizer = AutoTokenizer.from_pretrained( "facebook/bart-base" );
 ro_tokenizer = PreTrainedTokenizerFast.from_pretrained( "./ro_tokenizer.json" );
 ro_tokenizer.pad_token = en_tokenizer.pad_token
 
 def tokenize_dataset(sample):
 input = en_tokenizer(sample['en'], padding='max_length', max_length=120, truncation=True)
 label = ro_tokenizer(sample['ro'], padding='max_length', max_length=120, truncation=True)
 
 input["decoder_input_ids"] = label["input_ids"]
 input["decoder_attention_mask"] = label["attention_mask"]
 input["labels"] = label["input_ids"]
 
 return input
 
 train_tokenized = train.map(tokenize_dataset, batched=True)
 test_tokenized = test.map(tokenize_dataset, batched=True)
 validation_tokenized = validation.map(tokenize_dataset, batched=True)

from transformers import BartForConditionalGeneration
 from transformers import Seq2SeqTrainingArguments, Seq2SeqTrainer
 
 model = BartForConditionalGeneration.from_pretrained("facebook/bart-base" )
 
 training_args = Seq2SeqTrainingArguments(
 output_dir="./",
 evaluation_strategy="steps",
 per_device_train_batch_size=2,
 per_device_eval_batch_size=2,
 predict_with_generate=True,
 logging_steps=2,# set to 1000 for full training
 save_steps=64,# set to 500 for full training
 eval_steps=64,# set to 8000 for full training
 warmup_steps=1,# set to 2000 for full training
 max_steps=128, # delete for full training
 overwrite_output_dir=True,
 save_total_limit=3,
 fp16=False, # True if GPU
 )
 
 trainer = Seq2SeqTrainer(
 model=model,
 args=training_args,
 train_dataset=train_tokenized,
 eval_dataset=validation_tokenized,
 )
 
 trainer.train()