HomeBrowseAbout
Back to Browse

LLM internals

LLM internals

Expert
10 Sections
Sections
1

Foundations of Large Language Models: Architecture and Tokenization

Slides: 10Score: 0/0
2

Embedding Layers and Positional Encoding Mechanisms

Slides: 10Score: 0/0
3

Transformer Attention Mechanisms: Self-Attention and Cross-Attention

Slides: 10Score: 0/0
4

Feedforward Networks and Layer Normalization in LLMs

Slides: 10Score: 0/0
5

Training Paradigms: Pretraining, Fine-tuning, and Instruction Tuning

Slides: 10Score: 0/0
6

Optimization Techniques: Gradient Descent, Adam, and Learning Rate Schedules

Slides: 9Score: 0/0
7

Memory and Efficient Inference: Sparse Attention, Quantization, and Pruning

Slides: 10Score: 0/0
8

Handling Context Windows and Long-Range Dependencies

Slides: 10Score: 0/0
9

Scaling Laws and Model Parallelism Strategies

Slides: 10Score: 0/0
10

Evaluation, Bias Mitigation, and Safety Mechanisms in LLMs

Slides: 10Score: 0/0