Update README.md
Browse files
README.md
CHANGED
|
@@ -37,6 +37,10 @@ This model represents a step forward in developing the Polish language, demonstr
|
|
| 37 |
|
| 38 |
# Polish LLM Open Leaderboard
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
Sentiment Analysis (PolEmo2):
|
| 41 |
- In-domain accuracy: Matches Bielik at 77.70%
|
| 42 |
- Out-of-domain accuracy: Improved performance at 79.76% (vs 79.35%)
|
|
|
|
| 37 |
|
| 38 |
# Polish LLM Open Leaderboard
|
| 39 |
|
| 40 |
+
Core Leaderboards:
|
| 41 |
+
- MT-Bench-PL: slight decrease of 0.3 points (8.27 vs 8.56)
|
| 42 |
+
- Open PL LLM Leaderboard: improved performance by 0.09 points (65.80 vs 65.71)
|
| 43 |
+
|
| 44 |
Sentiment Analysis (PolEmo2):
|
| 45 |
- In-domain accuracy: Matches Bielik at 77.70%
|
| 46 |
- Out-of-domain accuracy: Improved performance at 79.76% (vs 79.35%)
|