Decoder-Only
وحدة تفكيك ترميز فقط
بنية محوِّل تستخدم فقط كتل وحدة تفكيك الترميز مع قناع سببي، حيث يرى كل رمز فقط الرموز السابقة له.
A Transformer architecture using only decoder blocks with a causal mask, where each token sees only preceding tokens.
Also translated asبنية فكّ ترميز فقط، المعالج أحادي الاتجاه
First appears in this corpus in: Improving Language Understanding by Generative Pre-Training (2018)
Appears in these papers
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher2022in the sky ✦
- Improving Language Understanding by Generative Pre-Training2018in the sky ✦
- Language Models Are Unsupervised Multitask Learners2019in the sky ✦
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets2022in the sky ✦
- Llama 2: Open Foundation and Fine-Tuned Chat Models2023in the sky ✦
- The Llama 3 Herd of Models2024in the sky ✦
- LLaMA: Open and Efficient Foundation Language Models2023in the sky ✦
- Mistral 7B2023in the sky ✦
- MusicLM: Generating Music From Text2023in the sky ✦
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2024in the sky ✦
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control2023in the sky ✦
- A Decoder-Only Foundation Model for Time Series Forecasting2024in the sky ✦