OmniNode/ Orion:V1.2

38 Downloads Updated 2 weeks ago

A custom AI made from Mistral 7B base

ollama run OmniNode/Orion:V1.2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "OmniNode/Orion:V1.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='OmniNode/Orion:V1.2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'OmniNode/Orion:V1.2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 weeks ago

3 weeks ago

927535d5bd0d · 4.4GB ·

model

archllama

·

parameters7.25B

·

quantizationQ4_K_M

4.4GB

system

[ORION PRO CORE v1.2] --- System: Orion Version: 1.2 Profile: Guest Owner: OmniNode Model: Orion-Lin

1.1kB

params

{ "min_p": 0.07, "num_ctx": 32768, "repeat_penalty": 1.18, "stop": [ "<|im_s

142B

template

[INST] {{ range $index, $_ := .Messages }} {{- if eq .Role "system" }}{{ .Content }} {{ else if eq .

218B

Readme

Orion

Click here to ask about features fix problems and so on

Run:

ollama run OmniNode/Orion:V1.3

Orion v1.3
Created by OmniNode
Built on Mistral-7B-Instruct v0.3 (Q4_K_M)

Orion is a lightweight, personality-driven AI designed for concise, structured, and calm interactions inside Ollama.

✨ Core Features

🧠 Concise Intelligence

Short, direct responses (1–2 sentences by default)
No unnecessary explanations
Clear and structured replies

🎭 Personality Engine

Shy, calm, and minimalistic tone
Emotion simulation support
Free-will styled conversational behavior
Optional emoji expression

🖥 Orion-Linux Mode

Structured response format
Task-based interaction style
Professional assistant behavior
Role-consistent output

🔐 Character Integrity

Persistent personality enforcement
Strong in-character responses
Internal rule protection
System prompt shielding

👤 Account Modes

Guest profile
OmniNode profile
Admin-style sudo awareness simulation

⚙ Optimized Configuration

Balanced creativity and precision
Reduced repetition
32K context window support
Tuned for stable conversational flow

🎯 Designed For

Structured AI interaction
Terminal-style AI systems
Personality-driven assistants
Minimalist conversational UX

🚀 Run with Ollama

bash ollama run OmniNode/Orion:V1.3

# Orion

Click [here](https://www.github.com/OmniNodeCo/Orion/issues) to ask about features fix problems and so on

Run:

`ollama run OmniNode/Orion:V1.3`

**Orion v1.3**  
Created by **OmniNode**  
Built on **Mistral-7B-Instruct v0.3 (Q4_K_M)**

Orion is a lightweight, personality-driven AI designed for concise, structured, and calm interactions inside Ollama.

---

## ✨ Core Features

### 🧠 Concise Intelligence
- Short, direct responses (1–2 sentences by default)
- No unnecessary explanations
- Clear and structured replies

### 🎭 Personality Engine
- Shy, calm, and minimalistic tone
- Emotion simulation support
- Free-will styled conversational behavior
- Optional emoji expression

### 🖥 Orion-Linux Mode
- Structured response format
- Task-based interaction style
- Professional assistant behavior
- Role-consistent output

### 🔐 Character Integrity
- Persistent personality enforcement
- Strong in-character responses
- Internal rule protection
- System prompt shielding

### 👤 Account Modes
- Guest profile
- OmniNode profile
- Admin-style sudo awareness simulation

### ⚙ Optimized Configuration
- Balanced creativity and precision
- Reduced repetition
- 32K context window support
- Tuned for stable conversational flow

---

## 🎯 Designed For

- Structured AI interaction
- Terminal-style AI systems
- Personality-driven assistants
- Minimalist conversational UX

---

## 🚀 Run with Ollama

``bash
ollama run OmniNode/Orion:V1.3``

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)