How to use AmPac/trace 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("AmPac/trace") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)
How to use AmPac/trace with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "AmPac/trace" --prompt "Once upon a time"
https://huggingface.co/AmPac/trace/resolve/main/train.png
hf download hf://AmPac/trace/train.png
curl -L -o train.png https://huggingface.co/AmPac/trace/resolve/main/train.png
