From 447de65d8334cff8db444069543f4f43ae6b66f5 Mon Sep 17 00:00:00 2001 From: "l.gabrysiak" Date: Fri, 28 Feb 2025 21:43:06 +0100 Subject: [PATCH] mod allegro --- allegro.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/allegro.py b/allegro.py index 92f20d3..dfc74bb 100644 --- a/allegro.py +++ b/allegro.py @@ -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)