Upstream Bonsai sources, Apple Silicon derivatives, and clearly labeled experimental oQe calibration artifacts.
TiGa PRO
TiGa-RCE
·
AI & ML interests
Training
Recent Activity
published an article 14 days ago
Watching Training Move: Causal Forecasting of Neural Updates Across 8,192 SGD Transitions updated a Space 15 days ago
TiGa-RCE/ald-tao-gpu published a Space 16 days ago
TiGa-RCE/ald-tao-gpuOrganizations
Thirty public MLX embedding checkpoints with explicit BF16 provenance, Q/oQ/oQe lineage, and matched representation-fidelity evaluation.
-
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q4
Feature Extraction • 0.6B • Updated • 12 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4
Feature Extraction • 0.6B • Updated • 9 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e
Feature Extraction • 0.6B • Updated • 17 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6
Feature Extraction • 0.6B • Updated • 9
Upstream Bonsai sources, Apple Silicon derivatives, and clearly labeled experimental oQe calibration artifacts.
Thirty public MLX embedding checkpoints with explicit BF16 provenance, Q/oQ/oQe lineage, and matched representation-fidelity evaluation.
-
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q4
Feature Extraction • 0.6B • Updated • 12 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4
Feature Extraction • 0.6B • Updated • 9 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e
Feature Extraction • 0.6B • Updated • 17 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6
Feature Extraction • 0.6B • Updated • 9