Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
politician
on Dec 8, 2023
|
parent
|
context
|
favorite
| on:
Mistral "Mixtral" 8x7B 32k model [magnet]
Honest question: Why isn't this on Huggingface? Is this one a leaked model with a questionable training or alignment methodology?
EDIT: I mean, I guess they didn't hack their own twitter account, but still.
kcorbitt
on Dec 8, 2023
[–]
It'll be on Huggingface soon. This is how they dropped their original 7B model as well. It's a marketing thing, but it works!
politician
on Dec 8, 2023
|
parent
|
next
[–]
Ah, well, ok. I appreciate the torrent link -- much faster distribution.
ComputerGuru
on Dec 8, 2023
|
root
|
parent
|
next
[–]
Also more reliable. I had to write my own script to clone hf repos on Windows because git+lfs to an smb share would only partially download.
politician
on Dec 8, 2023
|
parent
|
prev
[–]
@kcorbitt Low priority, probably not worth an email: Does using OpenPipe.ai to fine-tune a model result in a downloadable LoRA adapter? It's not clear from the website if the fine-tune is exportable.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
EDIT: I mean, I guess they didn't hack their own twitter account, but still.