-
Berbasis Transformer
-
Model berukuran terbesar dengan parameter lebih dari 10 kali lipat dibanding BERT-Large 340M, RoBERTa 355M, dan OpenAI GPT-2 1.5b
-
Dimungkinkan berkat DeepSpeed dan ZeRO
Bahkan ringkasan di halaman pengenalannya sendiri dikatakan dibuat oleh Turing-NLG
"Turing Natural Language Generation (T-NLG) is a 17 billion parameter language model by Microsoft that outperforms the state of the art on many downstream NLP tasks. We present a demo of the model, including its freeform generation, question answering, and summarization capabilities, to academics for feedback and research purposes."
Belum ada komentar.