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

New Model: Starling-LM-11B-alpha-v1 (alien.top)

submitted 1 year ago by perlthoughts@alien.top to c/localllama@poweruser.forum

44 comments fedilink hide all child comments

https://huggingface.co/NurtureAI/Starling-LM-11B-alpha-v1

This is Berkeley's model: Starling-LM-7B-alpha with the size of model increased to 11B from 7B.
Special thanks to user Undi95 for their mistral passthrough explanation with cg123's mergekit, Berkeley of course for Starling-LM-7B-alpha, and also everyone contributing to open source AI development.

Together we are strong!

The performance of this model will increase drastically as it is further fine tuned with the newly added layers.

AWQ version and GGUF version coming soon!

you are viewing a single comment's thread
view the rest of the comments

[–] Creative_Bottle_3225@alien.top 1 points 1 year ago (1 children)

I tried this model a little while ago with LM Studio and I noticed that it does not have GPU acceleration. Sin

[–] ex-arman68@alien.top 1 points 1 year ago

I noticed the same: in LM Studio I cannot enable Apple Metal (GPU), and I get the message: "Metal acceleration is not yet supported for this model architecture ('starcoder')". However, according to Activity Monitor, it fully uses the GPU when it runs. And it is very fast!