Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
moffkalast
on May 18, 2023
|
parent
|
context
|
favorite
| on:
Numbers every LLM developer should know
Yeah that's the split layer mode I mentioned. With 6G one can do about 18 layers, which is less than half of the 40 total for 13B.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: