Single-layer, single-head neural transformer written in PDP-11 assembly language

Lobsters·3 points·raymii·6 months ago·github.com

Paper Tape is All You Need. Contribute to dbrll/ATTN-11 development by creating an account on GitHub.

Read the full article at github.com →

#single #assembly #written #layer #transformer #neural #pdp #head

Related stories

Show HN: Strata – an expressive semantic layer that can say no to your LLMstrata.do
Hacker News · 18 points · about 13 hours ago
Transformer: A Novel Neural Network Architecture for Language Understandingresearch.googleblog.com
Lobsters · 4 points · about 9 years ago
Laya vs Jev head-to-head on identical inputsgithub.com
Hacker News · 1 points · 9 days ago
systemd's mstack tool mounts a single-layer directory writable by defaultdev.to
DEV Community · 5 points · 5 days ago
PSSA: A non-transformer language model written from scratch in Rustgithub.com
Hacker News · 77 points · 1 day ago
The mystery animal on an ancient god's headsignoregalilei.com
Hacker News · 141 points · 9 days ago

Related topics

e2ee8 suite16 aurionmail4 cryptpad4 x2f303 file69 binary20 line36 like208 app221 password10 without129