Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
FreakyT
on Dec 6, 2020
|
parent
|
context
|
favorite
| on:
Hardware-Accelerated TensorFlow and TensorFlow Add...
Has anyone tried using this with GPT-2? I’m curious if it would run locally at usable speeds.
kg
on Dec 6, 2020
|
next
[–]
GPT-2 appears to require at least 24GB of memory, so if that's accurate absolutely not.
minimaxir
on Dec 6, 2020
|
parent
|
next
[–]
You can load the 1.5B GPT-2 into a 16GB VRAM GPU...with fp16 downcasting. Still not ideal for M1 though.
minimaxir
on Dec 6, 2020
|
prev
[–]
For the small 124M model, it’s already runable on the CPU.
It’s going beyond that is tricky.
FreakyT
on Dec 6, 2020
|
parent
[–]
I’ve run the 1.5B model on my CPU, and it works...just very very slowly.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
