MLX bf16 conversion of deepreinforce-ai/Ornith-1.0-35B for Apple Silicon (mlx-vlm).
deepreinforce-ai/Ornith-1.0-35B (license: mit)mlx-vlm 0.6.3 — mlx_vlm.convert --hf-path deepreinforce-ai/Ornith-1.0-35B --mlx-path . --dtype bfloat16experts.{i}.gate_proj/up_proj/down_proj), while mlx-vlm expects a fused/stacked experts.gate_up_proj. A sanitize monkeypatch fused them before conversion (gate then up, stacked over experts).from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/Ornith-1.0-35B-mlx-bf16")
model-00001-of-00014.safetensors 5.3 GBmodel-00013-of-00014.safetensors 5.1 GBmodel-00005-of-00014.safetensors 5.1 GBmodel-00009-of-00014.safetensors 5.1 GBmodel-00010-of-00014.safetensors 5.0 GBmodel-00006-of-00014.safetensors 5.0 GBmodel-00012-of-00014.safetensors 5.0 GBmodel-00011-of-00014.safetensors 5.0 GBmodel-00007-of-00014.safetensors 5.0 GBmodel-00004-of-00014.safetensors 5.0 GBmodel-00002-of-00014.safetensors 5.0 GBmodel-00008-of-00014.safetensors 5.0 GBmodel-00003-of-00014.safetensors 5.0 GBmodel-00014-of-00014.safetensors 4.3 GBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ToPo-ToPo/Ornith-1.0-35B-mlx-bf16 ./model-folderdeepreinforce-ai/Ornith-1.0-35B