metadata
license: apache-2.0
base_model:
- google/gemma-3-1b-it
library_name: mlx
tags:
- mlx
- lora
- emotional-support
- macos
Baro 1.0 (MLX – Mac)
Baro is a presence-based emotional companion. It does not give advice, motivation, or solutions. It responds with calm reassurance and emotional presence.
Requirements
- Apple Silicon Mac
- Python 3.10+
- mlx-lm installed
Installation
Make sure you have Python 3.10 or newer.
Install MLX language tools:
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
echo >> ~/.zprofile
echo 'eval "$(/opt/homebrew/bin/brew shellenv zsh)"' >> ~/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv zsh)"
brew install git git-lfs
python3 -m pip install mlx-lm huggingface_hub
Base model download(enter ur hf token):
export HF_TOKEN=hf_xxxxx
git clone https://huggingface.co/umar141/Baro-mlx-mac-1.0
cd Baro-mlx-mac-1.0
git lfs pull
mlx_lm.convert \
--hf-path google/gemma-3-1b-it \
--mlx-path gemma-1b-mlx
Usage
mlx_lm.generate \
--model gemma-1b-mlx \
--adapter-path baro_1.0 \
--system-prompt system_prompt.txt \
--max-tokens 130 \
--temp 0.6 \
--top-p 0.9 \
--top-k 40 \
--min-p 0.05 \
--extra-eos-token "\n\n" \
--prompt "I feel empty and tired lately."