Adding Evaluation Results

README.md

@@ -2,6 +2,101 @@
 license: apache-2.0
 library_name: transformers
 tags: []
+model-index:
+- name: nox-solar-10.7b-v4
+  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: 37.53
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      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: 26.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      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: 0.68
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      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: 7.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      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: 12.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      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: 25.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=davidkim205/nox-solar-10.7b-v4
+      name: Open LLM Leaderboard
 ---
 
 # nox
@@ -40,3 +135,17 @@ Through this, users are expected to be able to freely conduct research and devel
 | model                               | Average     | Ko-TruthfulQA_mc1 | Ko-MMLU | Ko-HellaSwag | Ko-CommonGen V2 | Ko-ARC-Easy | kobest | kobest_boolq | kobest_copa | kobest_hellaswag | kobest_sentineg | kobest_wic |
 | ----------------------------------- | ----------- | ----------------- | ------- | ------------ | --------------- | ----------- | ------ | ------------ | ----------- | ---------------- | --------------- | ---------- |
 | davidkim205/nox-solar-10.7b-v4      | 69.48       | 63.16             | 48.59   | 85.93        | 87.21           | 71.16       | 60.8   | 55.91        | 77.5        | 57               | 89.67           | 48.81      |
+
+# [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_davidkim205__nox-solar-10.7b-v4)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.49|
+|IFEval (0-Shot)    |37.53|
+|BBH (3-Shot)       |26.63|
+|MATH Lvl 5 (4-Shot)| 0.68|
+|GPQA (0-shot)      | 7.61|
+|MuSR (0-shot)      |12.56|
+|MMLU-PRO (5-shot)  |25.92|
+