Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
coder543
on Dec 21, 2023
|
parent
|
context
|
favorite
| on:
Mistral 7B Fine-Tune Optimized
The article shows (fine tuned) Mistral 7B outperforming GPT-4, never mind GPT-3.5.
m3kw9
on Dec 21, 2023
[–]
This model is not close to even 3.5 from when I used it. It first of all does not follow instructions properly and it just runs on and on
coder543
on Dec 21, 2023
|
parent
[–]
What you're describing is the behavior you get from
any
base model that has not been instruction-tuned. The article is clear that this model is not for "direct use". It needs tuning for a specific application.
m3kw9
on Dec 21, 2023
|
root
|
parent
[–]
how does one fine tune it to follow instructions? I would have thought they have open source training set for these instruction-follow fine tunes?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
