D1A builds for ONNX Runtime's CPU execution provider: Android or any CPU. Decisions and chat from one graph.
🔄 In a Training Loop
JP
JohnP1
webbrain-one-520369's profile picture
johnlu0x's profile picture
webbrain-one-724833's profile picture·
AI & ML interests
None yet
Recent Activity
updated a model about 23 hours ago
JohnP1/d1a-e4b-it-coreml-4bit updated a model about 23 hours ago
mlx-community/d1a-e4b-it-8bit updated a model about 23 hours ago
JohnP1/d1a-e4b-it-mlx-q4Organizations
D1A builds for ONNX Runtime's CPU execution provider: Android or any CPU. Decisions and chat from one graph.
D1A decision models as PyTorch checkpoints (LoRA adapter + pointer head on Gemma 4), for CUDA GPUs, CPUs and any non-Apple platform.
D1A decision models converted to Core ML for the Apple Neural Engine (iPhone, iPad, Mac). Pilot.
D1A decision models as MLX exports, for Apple Silicon GPUs.