Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
RLHF progress: Scaling DPO to 70B, DPO vs. PPO update, Tülu 2, Zephyr-β
(
interconnects.ai
)
2 points
by
EvgeniyZh
on Nov 22, 2023
|
hide
|
past
|
favorite
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
