Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
llwj
on Sept 12, 2023
|
parent
|
context
|
favorite
| on:
Fine-tune your own Llama 2 to replace GPT-3.5/4
I see wrong responses about 1% of the time, but I love it, considering parsing raw text output without function calling had a much higher error rate.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
