Technology ❯ Artificial Intelligence ❯ Model Architecture

Transformer Models

Decoder-Only Architecture Generative Pre-trained Transformers Rotary Position Embeddings Mixture of Experts Embedding Techniques Parameter Efficiency Dense Transformers

4 ARTICLES

2mo ago

IBM Releases Granite 4.2 Reasoning-Focused Open-Weight LLMs

The models prioritize long-context training, configurable reasoning modes, and agent-focused reinforcement learning to power enterprise agents and workflow automation.