Instructions to use austindixson/skill-cartridges with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use austindixson/skill-cartridges with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("austindixson/skill-cartridges") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use austindixson/skill-cartridges with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "austindixson/skill-cartridges" --prompt "Once upon a time"
- Atomic Chat
Add pipeline tag and project page link
This PR adds the missing pipeline_tag: text-generation to the model card metadata, ensuring the repository is correctly categorized and discoverable on the Hub. It also adds a link to the paper’s project page for easier access.
Thanks, Niels. The pipeline_tag: text-generation is right and I'm glad to have it, so I'm merging this.
One adjustment: agenticlearning.ai/deleting-weights is the project page for Lu et al.'s Deletion Tuning paper, which these masks are built on, not the page for this repo. To avoid implying these are their official artifacts, I'm moving that link from the top of the card into the "Built on Deletion Tuning" credit, next to their arXiv, code and masks links. This repo's own project page is github.com/austindixson/skill-cartridges.