TR-HASH Vision v8 Collection Pretraining checkpoint, supervised refinement and live ComfyUI demo for TR-HASH Vision v8. • 3 items • Updated Aug 21 • 1
TR-HASH MoE 200M — 130B to 160B Research Release Collection TR-HASH MoE 200M base model, training checkpoints, interrupted 160B-token refinement, completed LoRA post-training, and live Space. • 4 items • Updated Sep 2 • 1
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning Paper • 2604.07242 • Published Aug 12 • 4
view article Article Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era Reubencf • Mar 7 • 8