Document 50K minimum

README.md

@@ -21,7 +21,7 @@ tags:
 
 Can a language model that only ever read text (e.g. FineWeb-edu) play Tetris **without any training on the game**?
 
-Pick 2+ decoder-only models (≤ 250M parameters, custom architectures welcome), watch them play the **same piece
+Pick 2+ decoder-only models (50K–250M parameters, custom architectures welcome), watch them play the **same piece
 sequence** side by side on CPU, and see their **Elo** change on a public leaderboard.
 
 ## How a model plays
@@ -70,6 +70,7 @@ Every ranked match (seed, model commit SHAs, scores, Elo before/after) is stored
 | `RESULTS_REPO` | `DedeProGames/lm-tetris-arena-results` | Dataset that stores the leaderboard |
 | `MAX_MODELS` | `4` | Language models per match |
 | `MAX_PARAMS` | `250000000` | Parameter limit |
+| `MIN_PARAMS` | `50000` | Smallest model allowed (smaller ones are rejected and removed from the leaderboard) |
 | `MAX_PIECES` | `500` | Piece cap per game |
 | `MAX_PARAM_GAP` | `20000000` | Largest size difference allowed in a ranked match |
 | `ALLOW_REMOTE_CODE` | `1` | Allow models with custom code (`trust_remote_code`) |