metadata

language:
  - en
license: apache-2.0
library_name: mlx
base_model: arcee-ai/Homunculus
tags:
  - distillation
  - /think
  - /nothink
  - reasoning-transfer
  - arcee-ai
  - mlx
pipeline_tag: text-generation

mlx-community/Homunculus-6bit

This model mlx-community/Homunculus-6bit was converted to MLX format from arcee-ai/Homunculus using mlx-lm version 0.25.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Homunculus-6bit")

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)