The purpose of this model is for use with
K8sGPT for fault analysis and resolution. Ultimately the resulting LLM is intended to be self-hosted in a GPU free environment running under
local-ai in Kubernetes.
The model was finetuned on
andyburgin/kubefix which contains a series of Question and Answer pairs generated from a subset of the Kubernetes documentation from the
English markdown files. The Q&A pairs have been generated from the documents using an opensource model (to avoid licencing issues for some free models or SaasS services) - after much trial and error the
openchat-3.5-0106 model was found to be the least problematic.
For a detailed description of the method used to generate the
andyburgin/kubefix dataset and this model please see the
kubefix-llm repo.
This model and dataset are under development and v0.1 is the very first release and is likely to need much optimisation and development.
Contributions are welcome to this repository! If you have improvements or suggestions, feel free to create a pull request.
Please note - the dataset and resultant model should be considered highly experimental and used with caution, use at your own risk.
