this post was submitted on 16 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Oh We Were So Close, Little 7b Buddy (alien.top)
submitted 1 year ago by luncheroo@alien.top to c/localllama@poweruser.forum
8 comments fedilink hide all child comments
 
top 8 comments
sorted by: hot top controversial new old
[–] ShiftyTys@alien.top 1 points 1 year ago

That's actually fkn hilarious

[–] Binliner42@alien.top 1 points 1 year ago

What is this GUI?

[–] gar1t@alien.top 1 points 1 year ago (1 children)

The Gambler benchmark: 0.96

[–] luncheroo@alien.top 1 points 1 year ago

I'm going to petition Huggingface to add it.

[–] TheManicProgrammer@alien.top 1 points 1 year ago

May I ask what preset are you using? In my LMStudio it cannot seem to find a correct one

[–] BrainSlugs83@alien.top 1 points 1 year ago (1 children)

How does the q8_0 version of that model do?

[–] luncheroo@alien.top 1 points 1 year ago

I'm sorry to not be able to report this. I usually aim for the Q5_K_M models due to current hardware limitations with my system.

[–] TheManicProgrammer@alien.top 1 points 1 year ago

Ok thank you!