Skip to content
All tags

#gpt-2

2 posts
ai deep-dive Reading CMU 07-280

CMU 07-280 Lecture 20: From Position Encoding to Causal Self-Attention

Lecture 20 expands one-token embeddings into sequences, adds positional information, derives Q/K/V scaled dot-product attention and causal masking, and assembles multi-head blocks into a GPT-2 skeleton.

#cmu#ai-course#transformer#attention#gpt-2
ai deep-dive Reading CMU 07-280

CMU 07-280 Stage Review II: Building AlexNet and GPT-2 as Working Systems

Stage II uses HW8 and HW11 to test whether representation, computation graphs, training, transfer, and generation actually connect, rather than treating CNNs and Transformers as diagrams to memorize.

#cmu#ai-course#alexnet#gpt-2#deep-learning