This model was converted to MLX format from
louisbrulenaudet/Pearl-3x7B using mlx-vlm version
0.16.1.
Refer to the
original model card for more details on the model.
1pip install -U mlx-vlm
2python -m mlx_vlm.generate --model mlx-community/Pearl-3x7B --max-tokens 100 --temp 0.0
1from mlx_lm import load, generate
2
3model, tokenizer = load("mlx-community/Pearl-3x7B")
4response = generate(model, tokenizer, prompt="hello", verbose=True)
If you use this code in your research, please use the following BibTeX entry.
1@misc{louisbrulenaudet2024,
2 author = {Louis Brulé Naudet},
3 title = {Pearl-3x7B, an xtraordinary Mixture of Experts (MoE) for data science},
4 year = {2024}
5 howpublished = {\url{https://huggingface.co/mlx-community/Pearl-3x7B}},
6}
If you have any feedback, please reach out at
louisbrulenaudet@icloud.com.
