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 5 days ago
Training a Looped Transformer: When to Repeat, Review, and Stop updated a dataset 21 days ago
TiGa-RCE/sno-article-1-evidence published a dataset 21 days ago
TiGa-RCE/sno-article-1-evidenceOrganizations
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 • 24 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4
Feature Extraction • 0.6B • Updated • 21 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e
Feature Extraction • 0.6B • Updated • 32 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6
Feature Extraction • 0.6B • Updated • 24
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 • 24 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4
Feature Extraction • 0.6B • Updated • 21 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e
Feature Extraction • 0.6B • Updated • 32 -
TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6
Feature Extraction • 0.6B • Updated • 24