Building on HF

nyuuzyou PRO

nyuuzyou

https://ducks.party/donate

AI & ML interests

None yet

Recent Activity

upvoted a paper about 2 hours ago

Arcee Trinity Large Technical Report

reacted to appvoid's post with 👍 about 4 hours ago

granite-4.0-350m, rwkv7-g1d-0.4b and LFM2-350M are currently the best sub 0.5b models currently for fewshot, simple language tasks no one is saying this: if you need the absolute speed + small size + quality, granite 350m is the current king

posted an update about 5 hours ago

🌍 Street-Level Imagery Dataset https://huggingface.co/datasets/nyuuzyou/streetview 934,191 image records index Eastern Europe and Northern Asia. Temporal links map historical views at identical coordinates across nine years. Key Stats: - 905,940 unique images - Coverage spanning 2016 to 2025 - Average 14.3 historical links per location Geographic bounds span 20.49° E to 152.32° E. Urban centers show higher data density.

View all activity

Organizations

Posts 83

Post

🌍 Street-Level Imagery Dataset nyuuzyou/streetview

934,191 image records index Eastern Europe and Northern Asia. Temporal links map historical views at identical coordinates across nine years.

Key Stats:

- 905,940 unique images
- Coverage spanning 2016 to 2025
- Average 14.3 historical links per location

Geographic bounds span 20.49° E to 152.32° E. Urban centers show higher data density.

Post

420

🎰 Casino Benchmark: Dataset + Space
nyuuzyou/casino-benchmark
nyuuzyou/casino-benchmark

14 models faced 1,400 simulations of heads-up Blackjack and European Roulette. Shared seeds locked identical cards and spins for each.

Key Stats:

- 14 models benchmarked
- 59,483 rows
- 35 MB compressed Parquet
- 35,000 scored decisions
- Full prompts, JSON responses, reasoning traces, latency
- Bankroll tracking from $1,000 start per run

Live leaderboard tracks bets, hits, stands, and risk management.
Gemini 3 Flash leads at +$3,396. Claude 4.5 Haiku at -$7,788.
Traces in the dataset. Leaderboard in the space.

View all Posts