README.md

metadata

language:
  - en
license: llama3.1
library_name: mlx
tags:
  - Llama-3.1
  - Instruct
  - loyal AI
  - fingerprint
  - finetune
  - chat
  - gpt4
  - synthetic data
  - roleplaying
  - unhinged
  - funny
  - opinionated
  - assistant
  - companion
  - friend
  - mlx
base_model: SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
pipeline_tag: text-generation

mlx-community/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-4bit

This model mlx-community/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-4bit was converted to MLX format from SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B using mlx-lm version 0.25.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)