igorcruz/fedora

igorcruz/ fedora:latest

9 Downloads Updated 3 days ago

A lightweight, CPU-optimized LLM tailored for Linux command-line environments. Built specifically for low-resource hardware, shell-based workflows, and rapid CLI task execution without requiring dedicated GPU acceleration.

tools

ollama run igorcruz/fedora

curl http://localhost:11434/api/chat \
  -d '{
    "model": "igorcruz/fedora",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='igorcruz/fedora',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'igorcruz/fedora',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 days ago

3 days ago

951aa0e9a449 · 2.0GB

model

archllama

parameters3.21B

quantizationQ4_K_M

2.0GB

license

LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreemen

7.7kB

license

**Llama 3.2** **Acceptable Use Policy** Meta is committed to promoting safe and fair use of its tool

6.0kB

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

96B

system

You are a friendly assistant.

29B

template

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{{

1.4kB

Readme

Model Overview: `igorcruz/fedora`

Base Model: Llama 3.2 (llama3.2)
System Persona: Configured with a custom system prompt: “You are a friendly assistant.”
Target Audience: Linux command-line users seeking a friendly local AI assistant via terminal.
Registry: Published and available on Ollama Hub under igorcruz/fedora.

Quick CLI Execution

To download and run this custom model directly in your Linux terminal:

ollama run igorcruz/fedora

Build & Release Workflow

Base Model Fetch: Pulled official llama3.2 weights from the Ollama library.
Modelfile Definition: Created a customized Modelfile setting llama3.2 as the parent image and defining the system persona.
Local Build: Compiled the customized image binary using ollama create -f Modelfile igorcruz/fedora.
Cloud Publish: Pushed the finalized model tag igorcruz/fedora to the remote Ollama model library for public accessibility.