Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
light
|
darkhn
ronyfadel
on Sept 12, 2023
|
parent
|
context
|
| on:
Fine-tune your own Llama 2 to replace GPT-3.5/4
It still does a much better job at translation than llama 2 70b even, at 6.7b params
two_in_one
on Sept 12, 2023
[–]
If it's MOE that may explain why it's faster and better...
yumraj
on Sept 12, 2023
|
parent
[–]
MOE?
sarthaksrinivas
on Sept 12, 2023
|
root
|
parent
[–]
Mixture of Experts Model -
https://en.wikipedia.org/wiki/Mixture_of_experts
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
|
Search:
