Jordan Dickens

The304network

·

AI & ML interests

None yet

Recent Activity

updated a bucket 13 days ago

The304network/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes-bucket

published a bucket 13 days ago

The304network/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes-bucket

reacted to Avifenesh's post with 🔥 13 days ago

I added a small gate to the Gated DeltaNet layers of Qwen3.5 and trained it with GRPO under a length penalty. On Qwen3.5-4B it reasons 48% shorter than LoRA on MATH-500, and anytime accuracy goes from 0.786 to 0.852. A LoRA with about the same parameter count barely moves. The gate sits on beta, the per-token write strength. One matrix per layer, zero init, so it starts as a no-op. It started as a negative eigenvalue experiment. The negative range turned out not to matter. The gate did. Write-up: https://huggingface.co/blog/Avifenesh/beta-gate-qwen35 Adapters: https://huggingface.co/collections/Avifenesh/gate-qwen35-6accb63081800b2f2d583b80 Code: https://github.com/avifenesh/gdn-beta-gatehttps://huggingface.co/collections/Avifenesh/gate-qwen35

View all activity

Organizations

None yet

The304network 's datasets

None public yet