Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mountainriver
on May 25, 2023
|
parent
|
context
|
favorite
| on:
How to Finetune GPT-Like Large Language Models on ...
I think it probably works a lot better, but I would love to see some research validating this
chadash
on May 25, 2023
[–]
I've read in a few places that it actually works worse in most cases. Much better to put the context in your prompt.
CuriouslyC
on May 25, 2023
|
parent
[–]
Fine tuning + context will outperform context alone, and it's cheaper to burn cycles fine tuning then use a smaller context than to use a larger context in production.
Guillaume86
on May 25, 2023
|
root
|
parent
[–]
Fine tuning + same context will probably outperform context alone, but if you use a smaller context that does not seem to work that well as GP stated.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: