Adding Evaluation Results (#2)

- Adding Evaluation Results (45a356237d07a8bf6d33d4f6d7568d3f30cba8cd)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,6 +1,7 @@
 ---
+language:
+- en
 license: apache-2.0
-pipeline_tag: text-generation
 tags:
 - chat
 - mistral
@@ -11,8 +12,102 @@ base_model:
 - anthracite-org/magnum-v2-12b
 - Sao10K/MN-12B-Lyra-v3
 - Gryphe/Pantheon-RP-1.6-12b-Nemo
-language:
-- en
+pipeline_tag: text-generation
+model-index:
+- name: StarDust-12b-v2
+  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: 56.29
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      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: 34.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      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: 5.97
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      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: 5.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      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: 14.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      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: 27.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6303fa71fc783bfc7443e7ae/c3ddWBoz-lINEykUDCoXy.png)
@@ -80,4 +175,17 @@ The following models were included in the merge:
 
 ### Special Thanks
 
-Special thanks to the SillyTilly and myself for helping me find the energy to finish this.
+Special thanks to the SillyTilly and myself for helping me find the energy to finish this.
+# [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/details_Luni__StarDust-12b-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.06|
+|IFEval (0-Shot)    |56.29|
+|BBH (3-Shot)       |34.95|
+|MATH Lvl 5 (4-Shot)| 5.97|
+|GPQA (0-shot)      | 5.82|
+|MuSR (0-shot)      |14.26|
+|MMLU-PRO (5-shot)  |27.10|
+