Part 8: LLM Fundamentals: Using GPT-2 as an Example
No matching items
jshn9515
2026-05-05
2026-08-28
| Title | Author | Date |
|---|---|---|
| 18.1 What Language Models Predict: Next-Token Prediction | jshn9515 | 2026-06-18 |
| 18.2 MiniGPT: From a Causal GPT Block to a Decoder-only Language Model | jshn9515 | 2026-06-20 |
| 18.3 Tokenizer: Characters, BPE, and Vocabulary | jshn9515 | 2026-06-18 |
| 18.4 Embedding, LM Head, and Weight Tying | jshn9515 | 2026-06-18 |
| 18.5 Training MiniGPT on TinyStories | jshn9515 | 2026-06-22 |
| 18.6 From Training to Generation: Temperature, Top-k, and Top-p | jshn9515 | 2026-06-18 |
| 18.7 GPT-2: From MiniGPT to a Pretrained Language Model | jshn9515 | 2026-06-23 |
| 19.1 Where Does the Memory Go When Training an LLM? Model States, Activations, and Runtime Overhead | jshn9515 | 2026-08-15 |