⚠️🔧⌨️🔥
@plausiblyreliable.com
The first place I saw this was the GPT-4 technical report. arxiv.org/pdf/2303.08774 p.12
August 8, 2025 at 11:46 PM
The first place I saw this was the GPT-4 technical report. arxiv.org/pdf/2303.08774 p.12
arxiv.org/abs/2304.13712
Transformers-on-text split broadly into Encoder-only (mostly tasks like sentiment analysis, entity extraction, representation), Encoder-Decoder (translation), and Decoder-only, which includes the GPT-likes and their descendants (text-completion models, chatbots, and so on)
Transformers-on-text split broadly into Encoder-only (mostly tasks like sentiment analysis, entity extraction, representation), Encoder-Decoder (translation), and Decoder-only, which includes the GPT-likes and their descendants (text-completion models, chatbots, and so on)
May 21, 2025 at 5:45 AM
arxiv.org/abs/2304.13712
Transformers-on-text split broadly into Encoder-only (mostly tasks like sentiment analysis, entity extraction, representation), Encoder-Decoder (translation), and Decoder-only, which includes the GPT-likes and their descendants (text-completion models, chatbots, and so on)
Transformers-on-text split broadly into Encoder-only (mostly tasks like sentiment analysis, entity extraction, representation), Encoder-Decoder (translation), and Decoder-only, which includes the GPT-likes and their descendants (text-completion models, chatbots, and so on)