How to use alexgusevski/LLaMA-Mesh-q6-mlx with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("alexgusevski/LLaMA-Mesh-q6-mlx") model = AutoModelForCausalLM.from_pretrained("alexgusevski/LLaMA-Mesh-q6-mlx")
How to use alexgusevski/LLaMA-Mesh-q6-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LLaMA-Mesh-q6-mlx alexgusevski/LLaMA-Mesh-q6-mlx
