How to use xquantize/k2-geoscience-7b-4bit-mlx 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("xquantize/k2-geoscience-7b-4bit-mlx") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)
How to use xquantize/k2-geoscience-7b-4bit-mlx with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "xquantize/k2-geoscience-7b-4bit-mlx" --prompt "Once upon a time"
https://huggingface.co/xquantize/k2-geoscience-7b-4bit-mlx/resolve/main/generation_config.json
hf download hf://xquantize/k2-geoscience-7b-4bit-mlx/generation_config.json
curl -L -o generation_config.json https://huggingface.co/xquantize/k2-geoscience-7b-4bit-mlx/resolve/main/generation_config.json
