Adding Evaluation Results

README.md

@@ -1,16 +1,16 @@
 ---
-license: apache-2.0
-base_model:
-- speakleash/Bielik-11B-v2
-- speakleash/Bielik-11B-v2.0-Instruct
-- speakleash/Bielik-11B-v2.1-Instruct
-- speakleash/Bielik-11B-v2.2-Instruct
 language:
 - pl
+license: apache-2.0
 library_name: transformers
 tags:
 - merge
 - mergekit
+base_model:
+- speakleash/Bielik-11B-v2
+- speakleash/Bielik-11B-v2.0-Instruct
+- speakleash/Bielik-11B-v2.1-Instruct
+- speakleash/Bielik-11B-v2.2-Instruct
 inference:
   parameters:
     temperature: 0.2
@@ -18,7 +18,103 @@ widget:
 - messages:
   - role: user
     content: Co przedstawia polskie godło?
-extra_gated_description: If you want to learn more about how you can use the model, please refer to our <a href="https://bielik.ai/terms/">Terms of Use</a>.
+extra_gated_description: If you want to learn more about how you can use the model,
+  please refer to our <a href="https://bielik.ai/terms/">Terms of Use</a>.
+model-index:
+- name: Bielik-11B-v2.3-Instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 55.83
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 38.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 8.01
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.08
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 16.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 27.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=speakleash/Bielik-11B-v2.3-Instruct
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -392,3 +488,17 @@ Members of the ACK Cyfronet AGH team providing valuable support and expertise:
 ## Contact Us
 
 If you have any questions or suggestions, please use the discussion tab. If you want to contact us directly, join our [Discord SpeakLeash](https://discord.gg/pv4brQMDTy).
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/speakleash__Bielik-11B-v2.3-Instruct-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.19|
+|IFEval (0-Shot)    |55.83|
+|BBH (3-Shot)       |38.06|
+|MATH Lvl 5 (4-Shot)| 8.01|
+|GPQA (0-shot)      |12.08|
+|MuSR (0-shot)      |16.01|
+|MMLU-PRO (5-shot)  |27.16|
+