SEARCH LAVACS
Find a topic across LavaCS
Search textbooks, study guides, six encyclopedias, experiments and comparisons.
10 results · page 1 of 1
Transformers and Large Language Models · Comparisons and explanations
Compare encoder-only, decoder-only, and encoder-decoder models by visibility, output construction, and task rather than assuming exclusive capabilities.
IntermediateTransformers and Large Language Models · Concepts and theorems
Separate causal and padding constraints, place masking before softmax, and account for position offsets when a KV cache is present.
IntermediateTransformers and Large Language Models · Concepts and theorems
Calculate input-output sequence budgets and distinguish configured length, truncation, retrieval, and effective use of long context.
IntermediateTransformers and Large Language Models · Concepts and theorems
Use small vectors to inspect dimensions, distance, and normalization, separating retrieval similarity from factual correctness.
IntermediateTransformers and Large Language Models · Concepts and theorems
Use sinusoidal coordinates and two-dimensional rotations to explain sequence order, separating positional representation from guaranteed long-context generalization.
IntermediateTransformers and Large Language Models · Concepts and theorems
Distinguish tokens from characters, bytes, and words, and inspect how IDs, normalization, and special tokens affect length and decoding.
IntermediateTransformers and Large Language Models · Experiments and implementations
Implement allowed-position attention and verify zero forbidden weights, row normalization, cached offsets, and explicit empty-row handling.
IntermediateTransformers and Large Language Models · Experiments and implementations
Use UTF-8, a combining character, and two explicit merge rules to reproduce differences between code points, bytes, and toy tokens.
IntermediateTransformers and Large Language Models · Study guides
Separate pretraining, fine-tuning and generation, then estimate the key/value cache for autoregressive decoding.
IntermediateTransformers and Large Language Models · Study guides
Trace token IDs into attention-weighted values while separating positions, masks and architectural variants.
Intermediate