Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
LoRA Learns Less and Forgets Less Updated
(
openreview.net
)
1 point
by
danielhanchen
74 days ago
|
hide
|
past
|
favorite
|
1 comment
danielhanchen
74 days ago
[–]
Updated research paper showing alpha = 2*rank for LoRA finetuning of LLMs gets much better results + other cool results!
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
