Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
a1j9o94
2 days ago
|
parent
|
context
|
favorite
| on:
Introspective Diffusion Language Models
You would only use the base model during training. This is a distillation technique
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
