Instructions to use mlx-community/IBM-granite-3.2-2b-instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/IBM-granite-3.2-2b-instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir IBM-granite-3.2-2b-instruct-4bit mlx-community/IBM-granite-3.2-2b-instruct-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Clarification on ibm-granite/granite-3.2-2b-instruct training origin
#1
by dqdw - opened
Dear [Developer/Team],
Thank you for your incredible contribution to the community with ibm-granite/granite-3.2-2b-instruct. It has been very helpful for my current project.
Before building on top of it, I would like to understand its connection with ibm-granite/granite-3.1-2b-instruct:
Direct Fine-tuning: Is it derived directly from ibm-granite/granite-3.1-2b-instruct, or through other checkpoints?
Inheritance: Is it fully compatible with the ibm-granite/granite-3.1-2b-instruct architecture?
I just want to make sure I'm using it the right way.
I really appreciate your help.