Foundation Model
نموذج أساسي
نموذج واسع النطاق مُدرَّب مسبقاً على بيانات شاملة يمكن تكييفه عبر التوجيه أو الضبط الدقيق أو النقل بدون تدريب لطيف واسع من المهام اللاحقة. من أمثلته GPT للغة وSAM للتجزئة.
A large-scale model pre-trained on broad data that can be adapted (via prompting, fine-tuning, or zero-shot transfer) to a wide range of downstream tasks. Examples include GPT for language and SAM for segmentation.
Also translated asالنموذج التأسيسي، الهيكل المعرفي الأولي، نموذج الأساس، نموذج القاعدة
First appears in this corpus in: A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence (1956)
Appears in these papers
- BLIP-2: Bootstrapping Language-Image Pre-Training with Frozen Image Encoders and Large Language Models2023in the sky ✦
- A Learning Algorithm for Boltzmann Machines1985in the sky ✦
- A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence1956in the sky ✦
- Deep Learning2015in the sky ✦
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024in the sky ✦
- DINOv2: Learning Robust Visual Features Without Supervision2023in the sky ✦
- DINOv2: Learning Robust Visual Features Without Supervision2023in the sky ✦
- Gaussian Processes for Machine Learning2006in the sky ✦
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017in 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 ✦
- LLaMA: Open and Efficient Foundation Language Models2023in the sky ✦
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces2023in the sky ✦
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2024in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- Segment Anything2023in the sky ✦
- Segment Anything2023in the sky ✦
- Video Generation Models as World Simulators2024in the sky ✦
- A Decoder-Only Foundation Model for Time Series Forecasting2024in the sky ✦
- Universal Language Model Fine-Tuning for Text Classification2018in the sky ✦