Update README.md
Browse files
README.md
CHANGED
|
@@ -49,6 +49,10 @@ Note:
|
|
| 49 |
2) By setting `<BLACK_WIN>` the model is being conditioned to predict moves where black wins
|
| 50 |
3) ELO level tokens for white and black will induce the model to play at the given ELO level.
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
## Uses
|
| 53 |
|
| 54 |
### Direct Use
|
|
@@ -99,3 +103,4 @@ In this representation, each chess move (half-move) corresponds to one token.
|
|
| 99 |
- Total training time: ~3 hours
|
| 100 |
|
| 101 |
|
|
|
|
|
|
| 49 |
2) By setting `<BLACK_WIN>` the model is being conditioned to predict moves where black wins
|
| 50 |
3) ELO level tokens for white and black will induce the model to play at the given ELO level.
|
| 51 |
|
| 52 |
+
## Evaluation
|
| 53 |
+
100m model performance against stockfish at various ELO levels
|
| 54 |
+
|
| 55 |
+
|
| 56 |
## Uses
|
| 57 |
|
| 58 |
### Direct Use
|
|
|
|
| 103 |
- Total training time: ~3 hours
|
| 104 |
|
| 105 |
|
| 106 |
+
|