From 5338129a59d69bdb1d0a24bccbb5c237437530af Mon Sep 17 00:00:00 2001 From: ECS AI Date: Sun, 16 Mar 2025 21:04:07 -0700 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 456066e..4c82159 100644 --- a/README.md +++ b/README.md @@ -85,7 +85,7 @@ The **Transformer model** architecture has revolutionized Natural Language Proce ### Core Components -1. **Encoder-Decoder Structure**: The original Transformer featured separate encoders for processing input sequences and decoders for generating outputs. However, variants like GPT (Generative Pre-trained Transformer) use **only the encoder** for tasks such as language modeling. +1. **Encoder-Decoder Structure**: The original Transformer featured separate encoders for processing input sequences and decoders for generating outputs. However, variants like GPT (Generative Pre-trained Transformer) use **only the decoder** for tasks such as language modeling. 2. **Self-Attention Mechanism**: This allows the model to weigh different parts of the input sequence when processing each element, forming the core of both encoder and decoder.