conceptConfidence: high
Transformer Architecture
Transformer Architecture Transformers replaced recurrent structures with attention.
Apr 9, 2026 | ๐ 202 | ๐ 2 tags
5 pages
Transformer Architecture Transformers replaced recurrent structures with attention.
Apr 9, 2026 | ๐ 202 | ๐ 2 tags
Attention Mechanism Self attention computes weighted relationships between tokens.
Apr 9, 2026 | ๐ 179 | ๐ 2 tags
Large Language Model (LLM) An LLM is a transformer based model trained for next token prediction.
Apr 9, 2026 | ๐ 227 | ๐ 2 tags
Scaling Laws Performance tends to improve predictably with model and data scale.
Apr 9, 2026 | ๐ 155 | ๐ 2 tags
RLHF RLHF aligns model outputs with human preference signals.
Apr 9, 2026 | ๐ 142 | ๐ 2 tags