Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sabareesh
5 months ago
|
parent
|
context
|
favorite
| on:
Reproducing GPT-2 in llm.c
This much bigger model (500M), P2P is enabled via Mailbox. It is expected because of memory to compute ratio
huac
5 months ago
[–]
can you elaborate?
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: