Hugging Face's logo
Activity Feed

AI & ML interests

Small language models, token routing, mixture-of-experts, multimodal generation, efficient training, open datasets, multilingual NLP and optimized inference.

Recent Activity
Pacific-i64  updated a collection about 2 hours ago
TR-HASH Vision v6 Research Release
Pacific-i64  updated a collection about 2 hours ago
TR-HASH Vision v6 Research Release
Pacific-i64  updated a collection about 2 hours ago
TR-HASH Vision v6 Research Release
View all activity

Organization Card
Community About org cards

AETHORIA AI

Open, efficient AI research

Community-led research into compact language models, deterministic token routing, multimodal generation and accessible training systems.

Partner of bench-labs ↗

Featured project

TR-HASH 0.5B

Base and instruction-tuned models, post-training data and interactive inference demo.

492M parameters TR-Hash MoE 20B pretraining tokens Open artifacts

Vision research

TR-HASH Vision v6

Compact hierarchical token-routed vision model with native multi-scale features, shifted-window attention and a lightweight detector. ImageNet-1K pretraining is active; COCO evaluation comes next.

0.76M pretrain ≈1M detector Hierarchical TR-Hash P2 + PAN + STAL DDP + Triton Evaluation pending

Datasets →

Atlas Posttrain Text instruction and chat SFT corpus Atlas Images 336K provenance-aware image-text pairs Atlas Image Edits 336K instruction-guided editing triplets
AETHORIA AI · Build, measure, share.

Collections 2

TR-HASH Vision v6 Research Release
Compact hash-routed vision research: ImageNet-1K pretraining, COCO and VOC detector checkpoints, and a live ComfyUI inference demo.
TR-HASH 0.5B Research Release
Research release for TR-HASH 0.5B: base and SFT models, post-training data, demos, and supporting artifacts.
TR-HASH Vision v6 Research Release
Compact hash-routed vision research: ImageNet-1K pretraining, COCO and VOC detector checkpoints, and a live ComfyUI inference demo.
TR-HASH 0.5B Research Release
Research release for TR-HASH 0.5B: base and SFT models, post-training data, demos, and supporting artifacts.