Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
MacsHeadroom
on March 12, 2023
|
parent
|
context
|
favorite
| on:
Large language models are having their Stable Diff...
Not per bit or per watt. LLaMA-30B is 16GB and draws 40 watts from a 4090 GPU.
yunyu
on March 13, 2023
[–]
LLaMa isn't instruction tuned
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
