Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,10 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
Our team at Czech Institute of Informatics, Robotics and Cybernetics focuses on developing NLP applications utilizing large language models.
|
| 11 |
+
As selecting the most capable model for a specific task and language is crucial for ensuring optimal performance, we concentrated our efforts on developing a Czech-focused LLM evaluation suite.
|
| 12 |
+
|
| 13 |
+
[CzechBench](https://github.com/jirkoada/czechbench_eval_harness/tree/main/lm_eval/tasks/czechbench) is a collection of Czech evaluation tasks selected to assess multiple aspects of LLM capabilities.
|
| 14 |
+
The suite newly leverages the Language Model Evaluation Harness, providing improved model compatibility and computation efficiency.
|
| 15 |
+
|
| 16 |
+
We are currently working on providing an open leaderboard for CzechBench to allow for easy sharing of evaluation results.
|