Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mluo
12 months ago
|
parent
|
context
|
favorite
| on:
DeepScaleR: Surpassing O1-Preview with a 1.5B Mode...
It's simply bc the model is small (1.5B), making it sensitive to weight perturbations
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
