|
--- |
|
language: en |
|
license: mit |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- Phi3 |
|
- kubernetes |
|
base_model: unsloth/Phi-3-mini-4k-instruct |
|
datasets: |
|
- andyburgin/kubefix |
|
--- |
|
|
|
# Phi-3-mini-4k-instruct-kubefix-v0.1-gguf: Fine-Tuned Phi3 for Kubernetes fault resolution |
|
|
|
The purpose of this model is for use with [K8sGPT](https://k8sgpt.ai/) for fault analysis and resolution. Ultimately the resulting LLM is intended to be self-hosted in a GPU free environment running under [local-ai](https://localai.io/basics/kubernetes/) in Kubernetes. |
|
|
|
The model was finetuned on [andyburgin/kubefix](https://huggingface.co./datasets/andyburgin/kubefix) which contains a series of Question and Answer pairs generated from a subset of the Kubernetes documentation from the [English markdown files](https://github.com/kubernetes/website/tree/main/content/en/docs). 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](https://huggingface.co./TheBloke/openchat-3.5-0106-GGUF) model was found to be the least problematic. |
|
|
|
For a detailed description of the method used to generate the [andyburgin/kubefix](https://huggingface.co./datasets/andyburgin/kubefix) dataset and this model please see the [kubefix-llm repo](https://github.com/andyburgin/kubefix-llm). |
|
|
|
**Model & Development** |
|
|
|
- **Developed by:** andyburgin |
|
- **License:** mit |
|
- **Finetuned from model:** unsloth/Phi-3-mini-4k-instruct |
|
|
|
**Key Features** |
|
|
|
- **Kubernetes Focus:** Optimised for fault analysis for Kubernetes clusters with [K8sGPT](https://k8sgpt.ai/). |
|
- **Knowledge Base:** Trained on a genrateed dataset from a subset of the Kubernetes documentation. |
|
- **Text Generation:** Generates informative and potentially helpful responses. |
|
|
|
**Important Note** |
|
|
|
This model and dataset are under development and v0.1 is the very first release and is likely to need much optimisation and development. |
|
|
|
**License** |
|
|
|
This model is distributed under the MIT License |
|
|
|
**Contributing** |
|
|
|
Contributions are welcome to this repository! If you have improvements or suggestions, feel free to create a pull request. |
|
|
|
**Disclaimer** |
|
|
|
Please note - the dataset and resultant model should be considered highly experimental and used with caution, use at your own risk. |
|
``` |