Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
minimaxir
on Aug 17, 2020
|
parent
|
context
|
favorite
| on:
Karpathy's MinGPT
GPT training performance on the CPU is funny. The vocab size and context window size have a
massive
effect on both speed and accuracy.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
