Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ Despite having only **30M parameters**, it is capable of competing with and occa
|
|
| 16 |
|
| 17 |
The model is based on the ChessSLM pre-train model, fine-tuned using RL with Stockfish to make the model to play more legal moves and attempt fewer illegal moves be rewarding good moves and bad moves.
|
| 18 |
|
| 19 |
-
Play against ChessSLM [here](https://flamef0x.github.io/other/chess).
|
| 20 |
|
| 21 |
---
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
The model is based on the ChessSLM pre-train model, fine-tuned using RL with Stockfish to make the model to play more legal moves and attempt fewer illegal moves be rewarding good moves and bad moves.
|
| 18 |
|
| 19 |
+
Play against ChessSLM [here](https://flamef0x.github.io/other/chess/chess).
|
| 20 |
|
| 21 |
---
|
| 22 |
|