π¨π½βπ Welcome to Episode 05 of “Tech Beats unplugged”
This time, we tried something completely crazy β we’re letting the AI hosts take over! That’s right π. We’re flipping the script and giving the AI the mic to guide us through the fascinating world of local LLMs. but that’s not all as this episode is actually inspired by my recent talk at Oracle Cloud World in Vegas. The topic? You guessed it: Local LLMs in the cloud.
π Weβre so excited to share our latest tech Beats show with youπ§‘!
We hope you’ll enjoy it!!!
Topics discussed:
- (00:00) Introduction
- (01:00) Why OpenAI Might Not Be Your BFF?
- (02:40) Local/Open LLMs to the Rescue!
- (03:38) What’s Quantization!
- (04:30) Where to find these Open LLMs?
- (05:02) Inference Engines (Ollama)!
- (05:50) What’s a modelfile!
- (06:40) What about deploying local AI to the cloud?(OKE/managed kubernetes)
- (07:30) From zero to cloud deployment Hero
- (08:28) What’s Next (LLM ethic benchmark)
- (09:55) Outro.
Show Notes
- My local LLM GitRepo: Ollama_lab
- Helm leaderboard for model safety: Sandford Helm model leaderboard
- My talks in Oracle cloud world 2024: OCW2024LLM