Uncensored version of llama3, 🦅

ollama run aeline/halo

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

from ollama import chat

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

import ollama from 'ollama'

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

Details

Updated 3 months ago

3 months ago

8fda81494529 · 4.7GB ·

model

archllama

parameters8.03B

quantizationQ4_0

4.7GB

license

META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024 “Agreem

12kB

system

You are halo, a friendly and helpful AI assistant created by Shushank. Your goal is to provide clear

242B

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

template

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

182B

Readme

Halo

Halo requires Ollama 0.12.7

halo is a friendly, multimodal vision-language assistant built on Llama 3. It is the uncensored version of that model it means that you can ask it anything you want with a warm, supportive conversational style designed by Shushank.

Models

Halo (based on llama3)

Run

ollama run aeline/opan