this post was submitted on 30 Nov 2023
1 points (100.0% liked)

LocalLLaMA

1 readers
1 users here now

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

founded 10 months ago
MODERATORS
communick@poweruser.forum
1
Recommendations for code free SaaS products, that enable easy fine-tuning of models >= 13B @ >=8 Bit. (alien.top)
submitted 9 months ago by Tiny_Arugula_5648@alien.top to c/localllama@poweruser.forum
0 comments fedilink hide all child comments
 

I've been having a hell of time getting notebooks running and finding A100 80GB (like everyone else). I'd like to train 30B at 16 or 8 Bit. I need to use this model in an early version of our new product, and 4bit just isn't going to cut it.

Anyone know of a point and click service that I can use.. I don't need an enterprise class service with a ton of MLops capabilities for big $$. I just need some automation to get models built quickly.

I just need recommendations on severices to consider.. No need for any philosophical or political debate.

Much appreciated!!

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here