#ai (2023-12)

Discuss all things related to AI

2023-12-04

venkata.mutyala avatar
venkata.mutyala
04:54:42 AM

I learned about this from a local meetup and it’s pretty cool: https://lmstudio.ai/

If you want to quickly run a LLM on your local machine it’s pretty dumb/simple to get started. I am using a macbook pro m1 pro w/ 16GB of ram.

:space_invader: LM Studio - Discover and run local LLMsattachment image

Find, download, and experiment with local LLMs

1
Hao Wang avatar
Hao Wang
02:14:16 PM

I use Ollama, looks similar

:space_invader: LM Studio - Discover and run local LLMsattachment image

Find, download, and experiment with local LLMs

venkata.mutyala avatar
venkata.mutyala
01:44:03 AM

Oh nice. Will check it out. Are there any local models you have been a big fan of?

1
Hao Wang avatar
Hao Wang
02:29:37 AM

Mistral or codellama

1
venkata.mutyala avatar
venkata.mutyala
02:30:33 AM

Cool I’ll check them out. How powerful is your machine?

Hao Wang avatar
Hao Wang
04:01:45 AM

I’ve got 64GB M1, feels very smooth to run the models, it saves time

1

2023-12-05

2023-12-06

venkata.mutyala avatar
venkata.mutyala
05:29:46 AM

https://github.com/bricks-cloud/BricksLLM

bricks-cloud/BricksLLM

Simplifying LLM ops in production

1
    keyboard_arrow_up