BSDA5004
14 Internal Entities Declared
📄
165 - Transformer Architecture — Complete IntroductionAccess ->
📄
166 - Self-Attention and QKV ComputationAccess ->
📄
167 - Multi-Head Attention Deep DiveAccess ->
📄
168 - Positional Encoding — Sinusoidal and Learned EmbeddingsAccess ->
📄
169 - Decoder Layer, Cross-Attention, and Teacher ForcingAccess ->
📄
170 - Layer Normalization & Residual Connections in TransformersAccess ->
📄
171 - Pre-training Objectives- Causal LM, Masked LM, and BeyondAccess ->
📄
172 - GPT Architecture- Decoder-Only Transformer & Autoregressive GenerationAccess ->
📄
173 - BERT Architecture- Encoder-Only & Bidirectional ContextAccess ->
📄
174 - Tokenization- BPE, WordPiece, SentencePieceAccess ->
📄
175 - Fine-tuning Methods- LoRA, Adapters, and PEFTAccess ->
📄
176 - Prompt Engineering- In-Context Learning, Chain-of-ThoughtAccess ->
📄
177 - RLHF, Alignment, and Constitutional AIAccess ->
📄
178 - Quantization, Pruning, Distillation & Fast AttentionAccess ->