Decoder-Only Model
نموذج فكّ الترميز فقط
بنية محوِّل تستخدم حزمة فكّ الترميز فقط مع قناع سببي يمنع النظر إلى الرموز المستقبلية، وتُولّد النص من اليسار لليمين.
A Transformer architecture using only the decoder stack with causal masking that prevents attending to future tokens, generating text left-to-right.
Also translated asنموذج المفكِّك فقط، نموذج فكّ التشفير أحادي الاتجاه
First appears in this corpus in: OPT: Open Pre-Trained Transformer Language Models (2022)
Appears in these papers
- BLIP-2: Bootstrapping Language-Image Pre-Training with Frozen Image Encoders and Large Language Models2023in the sky ✦
- Gemini: A Family of Highly Capable Multimodal Models2023in the sky ✦
- Gemma: Open Models Based on Gemini Research and Technology2024in the sky ✦
- Llama 2: Open Foundation and Fine-Tuned Chat Models2023in the sky ✦
- OPT: Open Pre-Trained Transformer Language Models2022in the sky ✦
- PaLM: Scaling Language Modeling with Pathways2022in the sky ✦
- Textbooks Are All You Need2023in the sky ✦
- Fast Inference from Transformers via Speculative Decoding2023in the sky ✦