LeoBorai/chile-seismological-records
Viewer • Updated • 58.1k • 1.37k
Leo Borai PRO
LeoBorai
AI & ML interests
🦀 Rust Software Engineer who enjoys messing around with Data Science and other Computer related topics.
Recent Activity
updated a dataset 1 day ago
LeoBorai/chile-seismological-records liked a Space 5 days ago
speridlabs/idol liked a model 17 days ago
Cloudflare/clefOrganizations
updated a
dataset 1 day ago
liked a
Space 5 days ago
liked a
model 17 days ago
liked a
Space 22 days ago
liked a
Space 23 days ago
liked a
model 30 days ago
upvoted an article 30 days ago
Article
How to Use the Jev AI Model: A Step-by-Step Developer Guide
sora-2
• • 52 updated 2
Spaces about 1 month ago
liked 5
Spaces about 1 month ago
Qwen-Image-2.1
🎨
527
Generate or edit images from text and optional photos
Jev Decision Index
🔬
902
Benchmarks and news on various repros of TypeSafe's Jev
Semantic Image Field
🌄
68
Multimodal Jev (a.k.a. CLIP)
Find a leaderboard
🔍
180
Explore and discover all leaderboards from the HF community
Meridian
🧭
66
Generate a new camera‑move video from your image or clip
reacted to DedeProGames's post with 🔥 about 1 month ago
Post
6,314
🧱 SLM Tetris Arena: can a small language model play Tetris without ever being trained on it?
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
- 1 reply
liked a
Space about 1 month ago
liked a
model about 1 month ago
updated a
dataset about 1 month ago
updated a
Space about 1 month ago
published a
Space about 1 month ago