corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a087ec-e4f4-72ad-a3dc-85b6d643ebb8

Decoder-Only vs. Encoder-Decoder: Architecture Trade-offs

thegustafson.com · published undated

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at thegustafson.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
14
Words captured
4,315

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
Self-Attention: Q, K, V from First Principles Read at the source ↗
thegustafson.com
Causal Masking and the Autoregressive Constraint Read at the source ↗
thegustafson.com
Layer Normalization: Pre-Norm, Post-Norm, and RMSNorm Read at the source ↗
thegustafson.com
Seq2seq, Bahdanau Attention, and Why Recurrence Hit a Wall Read at the source ↗
thegustafson.com
A Close Reading of ‘Attention Is All You Need’ Read at the source ↗
thegustafson.com
Language Modeling as Next-Token Prediction Read at the source ↗
thegustafson.com
https://arxiv.org/abs/1810.04805
arxiv.org
https://arxiv.org/abs/1910.10683
arxiv.org
https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf
cdn.openai.com
https://arxiv.org/abs/2005.14165
arxiv.org
https://arxiv.org/abs/2204.05832
arxiv.org
https://arxiv.org/abs/2212.04356
arxiv.org
https://arxiv.org/abs/1706.03762
arxiv.org
https://arxiv.org/abs/2001.08361
arxiv.org