Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
yorwba
4 months ago
|
parent
|
context
|
favorite
| on:
Fine-tuning LLMs is a waste of time
In addition to increasing the number of layers, you can also grow the weight matrices and initialize by tiling them with the smaller model's weights
https://neurips.cc/media/neurips-2023/Slides/83968_5GxuY2z.p...
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: