
-
WizardLM
Discontinued Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath
If you pair this with the latest WizardCoder models, which have a fairly better performance than the standard Salesforce Codegen2 and Codegen2.5, you have a pretty solid alternative to GitHub Copilot that runs completely locally.
-
Nutrient
Nutrient - The #1 PDF SDK Library. Bad PDFs = bad UX. Slow load times, broken annotations, clunky UX frustrates users. Nutrient’s PDF SDKs gives seamless document experiences, fast rendering, annotations, real-time collaboration, 100+ features. Used by 10K+ devs, serving ~half a billion users worldwide. Explore the SDK for free.
-
LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference
Here's my tutorial on how to run this setup on docker-compose to test it in a simple way
-
Here's an example on how to configure LocalAI with a WizardCoder prompt
-
Do you want to test this setup on Kubernetes? Here is my resources that deploy LocalAI on my cluster with GPU support. Not sure on how to use GPU with Kubernetes on homelab setups? I wrote an article explaining how I configured my k3s to run using Nvidia's drivers and how they integrate with containerd.
Related posts
-
ArgoCD // Helm Chart // Dev/Staging // Your Best-Practise
-
win cool stuff with kubefirst's new video game flappy-kray (oh and we have a new ui too i guess)
-
PSA: short-sha container names? guard your strings or face the eventual wrath of euler's number!!
-
Am I missing something? (argo cd and helm in AWS)
-
How to obtain professional Kubernetes experience?