CNWPlayer/Vega-SupraNeo-4M-Tetris-Verbose
Text Generation • 4.07M • Updated • 839
🌌 Vega 1.6 128M Tetris
CNWPlayer
CNWPlayer
P(doom) Rejects the premise
AI & ML interests
SLMs, LLMs, really anything that ends in LM.
Recent Activity
updated a model about 6 hours ago
CNWPlayer/Vega-SupraNeo-4M-Tetris-Verbose reacted to danielhanchen's post with 👀 about 7 hours ago
Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: https://huggingface.co/unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2 reacted to danielhanchen's post with 😎 about 7 hours ago
Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: https://huggingface.co/unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2Organizations
None yet
updated a
model about 6 hours ago
reacted to danielhanchen's post with 👀😎🔥❤️🚀 about 7 hours ago
Post
906
Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2
published a
model 4 days ago
updated a
model 4 days ago
liked a
model 4 days ago
reacted to DedeProGames's post with 🤗🧠🚀🔥 6 days ago
Post
6275
🧱 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
Hugging Science is DEAD???
➕ 2
37
#2 opened 12 days ago
by 
XBFDI
liked a
dataset 10 days ago
reacted to danielhanchen's post with 🔥 10 days ago
as a competitive tetris player i solved tetris
5
#3 opened 10 days ago
by CNWPlayer
published a
model 10 days ago
updated a
model 10 days ago
published a
model 10 days ago