Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
squeaky-clean
on July 6, 2023
|
parent
|
context
|
favorite
| on:
InternLM – new open source 7B LLM
Is that what nerfed means? I usually see "nerfed" used in a way that means that it will refuse to answer certain topics. "I can't answer that as it would violate copyright" and such.
cubefox
on July 6, 2023
[–]
The fine-tuned models are certainly censored and not "raw".
squeaky-clean
on July 6, 2023
|
parent
[–]
But doesn't code-davinci-002 also have OpenAI's filters in between you and the model?
cubefox
on July 7, 2023
|
root
|
parent
[–]
Yes, but that's different from the model itself being fine-tuned.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: