mod allegro
This commit is contained in:
parent
029662e9d1
commit
447de65d83
|
|
@ -11,7 +11,7 @@ dataset = load_dataset("wmt16", "ro-en")
|
|||
|
||||
# Przetwórz dane do formatu odpowiedniego dla modelu
|
||||
def tokenize_function(examples):
|
||||
return tokenizer(examples['translation'], truncation=True, padding='max_length', max_length=128)
|
||||
return tokenizer(examples['translation']['ro'], examples['translation']['en'], truncation=True, padding='max_length', max_length=128)
|
||||
|
||||
tokenized_datasets = dataset.map(tokenize_function, batched=True)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue