Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fpgaminer
9 months ago
|
parent
|
context
|
favorite
| on:
Tracing the thoughts of a large language model
LORA can be used in RL; it's indifferent to the training scheme. LORA is just a way of lowering the number of trainable parameters.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
