Useful Links
Computer Science
Artificial Intelligence
Generative AI
1. Introduction to Generative AI
2. Mathematical and Technical Foundations
3. Machine Learning Fundamentals
4. Core Generative Model Architectures
5. Transformer Architecture and Language Models
6. Text Generation Applications
7. Image and Visual Generation
8. Audio and Speech Generation
9. Development Lifecycle and Best Practices
10. Practical Implementation Tools
11. Ethical Considerations and Responsible AI
12. Legal and Regulatory Landscape
13. Economic and Social Impact
14. Future Directions and Emerging Trends
Transformer Architecture and Language Models
Transformer Fundamentals
Attention Mechanism
Scaled Dot-Product Attention
Multi-Head Attention
Attention Patterns
Positional Encoding
Sinusoidal Encoding
Learned Positional Embeddings
Relative Position Encoding
Layer Structure
Self-Attention Layers
Feed-Forward Networks
Residual Connections
Layer Normalization
Language Model Pretraining
Pretraining Objectives
Causal Language Modeling
Masked Language Modeling
Prefix Language Modeling
Scaling Laws
Parameter Scaling
Data Scaling
Compute Scaling
Training Infrastructure
Distributed Training
Mixed Precision Training
Gradient Accumulation
Large Language Models
GPT Family
GPT-1 Architecture
GPT-2 Scaling
GPT-3 Emergence
GPT-4 Capabilities
BERT and Bidirectional Models
BERT Pretraining
RoBERTa Improvements
DeBERTa Enhancements
Open Source Models
LLaMA Architecture
Falcon Models
MPT Models
Mistral Models
Fine-Tuning and Adaptation
Supervised Fine-Tuning
Task-Specific Adaptation
Few-Shot Learning
In-Context Learning
Instruction Tuning
Instruction Following
Multi-Task Learning
Chain-of-Thought Training
Reinforcement Learning from Human Feedback
Reward Modeling
Policy Optimization
Constitutional AI
Previous
4. Core Generative Model Architectures
Go to top
Next
6. Text Generation Applications