TR-HASH-MoE-100M-125B-Agentic-Pretraining

Description

TR-HASH-MoE-100M-125B-Agentic-Pretraining is an open-weight text-generation model with roughly 100M parameters published by AETHORIA-AI on the Hugging Face Hub. It has 603 downloads. Runs with pytorch.

Categories

• Coding

Tags

• tr_hash_moe
• tr-hash
• mixture-of-experts
• deterministic-routing
• multi-hash-routing
• agentic-pretraining
• gqa
• custom-code

Capabilities

• Text generation
• Library: pytorch
• 100M parameters