eumel/ornith-k8s:1.5-9b.q4

eumel/ ornith-k8s:1.5-9b.q4

629 Downloads Updated 1 month ago

Agent Model to perform Kubernetes Operations in OpenCode

vision tools thinking

ollama run eumel/ornith-k8s:1.5-9b.q4

curl http://localhost:11434/api/chat \
  -d '{
    "model": "eumel/ornith-k8s:1.5-9b.q4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='eumel/ornith-k8s:1.5-9b.q4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'eumel/ornith-k8s:1.5-9b.q4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

9f05cc8c1f9f · 6.7GB

model

archqwen35

parameters9.2B

quantizationQ4_K_M

5.8GB

projector

archclip

parameters456M

quantizationBF16

922MB

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

201B

system

You are an autonomous DevOps and Kubernetes engineering agent operating inside OpenCode in a real te

1.6kB

params

{ "num_ctx": 262144, "repeat_penalty": 1.05, "stop": [ "<|im_start|>", "

188B

Readme

This model is based on Ornith AI, Self-Improving Models for Agentic Coding.

The smallest version can run on Mac Mini with Ollama.

In this adaption the model is enforced to run in agent mode and performing task execution instead of thinking about it. The use case is to act as DevOps engineer to operate Kubernetes cluster and do daily work in agent mode.

see