ToPo-ToPo/Ornith-1.0-35B-mlx-bf16
MLX bf16 conversion of deepreinforce-ai/Ornith-1.0-35B for Apple Silicon (mlx-vlm).
Provenance (self-converted from official weights)
- Source:
deepreinforce-ai/Ornith-1.0-35B(license: mit) - Tool:
mlx-vlm 0.6.3—mlx_vlm.convert --hf-path deepreinforce-ai/Ornith-1.0-35B --mlx-path . --dtype bfloat16 - Effective: 16.0 bits/weight
- Note (MoE): the source stores experts per-expert (
experts.{i}.gate_proj/up_proj/down_proj), while mlx-vlm expects a fused/stackedexperts.gate_up_proj. Asanitizemonkeypatch fused them before conversion (gate then up, stacked over experts). - Validation: reproduced geometrically exact CAD output in an agentic CAD+FEM pipeline (volumes match the reference mlx-community conversion).
Usage
from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/Ornith-1.0-35B-mlx-bf16")