Hugging Face's logo
BB's picture
🀝 Open to Collab

BB

CodeByBB
1
webxos's profile picture PhysiQuanty's profile picture Quazim0t0's profile picture
Β·
https://dreambuild.cloud

AI & ML interests

⚑ π’·π“Šπ’Ύπ“π’Ήπ’Ύπ“ƒπ‘” 𝓉𝒽𝑒 π’»π‘œπ“Šπ“ƒπ’Ήπ’Άπ“‰π’Ύπ‘œπ“ƒπ“ˆ π‘œπ’» π“‰π‘œπ“‚π‘œπ“‡π“‡π‘œπ“Œβ€™π“ˆ π“π“–π“˜ π“ˆπ“Žπ“ˆπ“‰π‘’π“‚π“ˆ ⚑

Recent Activity

repliedto Quazim0t0's post 1 day ago
On-Fly-Jev is up: https://huggingface.co/Quazim0t0/On-Fly-Jev Second Jev-style model. First was Byrne-Jev (70M SpikeWhale). This one is a 96M spiking trunk - every unit is a copy of one of 100 real MaleCNS fly neurons - plus a typed-decision head. One forward pass. No generated text. I built it for speed. Typed-decisions test split, 400 cases, 2,000 decisions, 5 questions per case, local GPU: β€’ 7.3 ms p50 per decision (~137 / s) β€’ 36.6 ms p50 / 53.5 ms p95 per case of 5 β€’ ~27 cases / s Same protocol vs the others: β€’ On-Fly-Jev: 36.6 ms / case, ~137 decisions / s β€’ Byrne-Jev: 110.7 ms / case, ~45 / s β€’ ModernBERT-base: 349 ms / case, ~14 / s β€’ TypeSafe Jev 1.13 (hosted, so network is in it): 710 ms / case, ~7 / s About 3x Byrne-Jev, 9.5x ModernBERT, 19x TypeSafe Jev per case. Live ViZDoom, 1 question per tick including game I/O: 23.4 ms (~43 / s). β€’ Accuracy 0.666 (Byrne-Jev 0.630, Jev 1.13 0.727) β€’ ECE 0.045, same as Byrne-Jev, about a third of Jev 1.13 50/50 merge of two checkpoints from one run. Research artifact, not a chatbot. More videos are on the card.
liked a model 4 months ago
black-forest-labs/FLUX.1-schnell
updated a model 8 months ago
CodeByBB/1000s-websites
View all activity

Organizations

Stella's Vision's profile picture