{"id":16148179,"url":"https://github.com/chanwit/kube-7b","last_synced_at":"2025-04-06T21:19:55.351Z","repository":{"id":216481136,"uuid":"741442545","full_name":"chanwit/kube-7b","owner":"chanwit","description":null,"archived":false,"fork":false,"pushed_at":"2024-01-11T12:58:10.000Z","size":23,"stargazers_count":28,"open_issues_count":1,"forks_count":1,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-02-13T03:18:19.534Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chanwit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2024-01-10T12:06:26.000Z","updated_at":"2024-10-08T00:48:28.000Z","dependencies_parsed_at":"2024-01-11T18:00:06.068Z","dependency_job_id":null,"html_url":"https://github.com/chanwit/kube-7b","commit_stats":null,"previous_names":["chanwit/openkubelm","chanwit/kube-7b"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanwit%2Fkube-7b","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanwit%2Fkube-7b/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanwit%2Fkube-7b/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanwit%2Fkube-7b/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chanwit","download_url":"https://codeload.github.com/chanwit/kube-7b/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247551030,"owners_count":20957042,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-10T00:31:31.096Z","updated_at":"2025-04-06T21:19:55.331Z","avatar_url":"https://github.com/chanwit.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kube-7b\n\nKube-7b is a series of LLMs, designed to be your Cloud Native assistant.\nThis version of `kube-7b` is a fine-tuned version of Mistral 7B, learning from a 10k dataset related to Kubernetes and Cloud Native knowledge. It will answer your questions with Cloud Native context.\n\n## Why Kube-7b?\n\nCurrently, there is no suitable open-source model for providing assistance with Cloud Native-specific knowledge and context. Kube-7b is an effort to fill this gap. We recently achieved this following the release of `Mixtral 8x7B`, using it to synthesize high-quality datasets from public knowledge without relying on ChatGPT or GPT-4 APIs.\n\nWe have successfully used Mistral 8x7B to synthesize the initial dataset (`filtered_kube_10k`), which was then used to DPO fine-tune a variant of Mistral 7B. This resulted in `kube-7b`, the first model in our OpenKubeLM collection.\n\nWe use the tokenizer from Zephyr and the model is delivered as the GGUFv3 format supported by Ollama, Llamafile, and etc.\n\n### Getting Started with Ollama\n\nOllama is a CLI to run LLMs locally. To run this model with Ollama, please install it first by following the instructions [here](https://ollama.ai/download).\n\n```\nollama run chanwit/kube-7b:v0.1\n```\n\n### Getting Started with Llamafile\n\nDownload from: [https://huggingface.co/chanwit/kube-7b-v0.1-gguf/blob/main/kube-7b-v0.1.llamafile](https://huggingface.co/chanwit/kube-7b-v0.1-gguf/blob/main/kube-7b-v0.1.llamafile)\n\nHere's the `kube-7b` bash script to run the model with its system prompt.\n```shell\n(\necho \"\u003c|system|\u003e\nYou are a Kube AI assistant.\u003c/s\u003e\n\u003c|user|\u003e\n\"$@\"\u003c/s\u003e\n\u003c|assistant|\u003e\"\n) | ./kube-7b-v0.1.llamafile -t 8 --temp 0.1 2\u003e/dev/null\n```\n\nSave it as `./kube-7b` then run `./kube-7b \"What is Kubernetes?\"` to try the model.\n\n## Prompt\n\nThe models in this collection use the `zephyr` prompt format.\n\n# Contributions\n\nContributions to this project are greatly appreciated, specifically in the form of question and answer pairs, which will aid in the enhancement of future models. We are actively seeking contributions for a [new dataset centered around knowledge of Kubernetes 1.29](datasets/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchanwit%2Fkube-7b","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchanwit%2Fkube-7b","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchanwit%2Fkube-7b/lists"}