我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。
tokenized = tokenized[None, :] # Add batch dimension
tokenized_translation = trax.supervised.decoding.autoregressive_sample(model, tokenized, temperature = 0.0))
tokenized_translation = tokenized_translation[0][:-1]
translation = trax.data.detokenize(tokenized_translation, vocab_dir = 'gs://trax-ml/vocabs/', vocab_file = 'ende_32k.subword')
print("The sentence:", sentence)
print("The translation:", translation)
輸出結果為：
