Adding Evaluation Results (#6)

- Adding Evaluation Results (29f646e44e9940288aa7a8c7aeaba1e305179a4d)


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

README.md

@@ -2,6 +2,101 @@
 license: other
 license_name: qwen2
 license_link: https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE
+model-index:
+- name: Tess-v2.5.2-Qwen2-72B
+  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: 44.94
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      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: 52.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      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: 27.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      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: 13.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      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: 10.89
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      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: 50.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-v2.5.2-Qwen2-72B
+      name: Open LLM Leaderboard
 ---
 
 # Tess-v2.5.2 (Qwen2-72B)
@@ -118,3 +213,17 @@ While this model aims for accuracy, it can occasionally produce inaccurate or mi
 Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content. 
 
 Exercise caution and cross-check information when necessary. This is an uncensored model.
+
+# [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_migtissera__Tess-v2.5.2-Qwen2-72B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |33.28|
+|IFEval (0-Shot)    |44.94|
+|BBH (3-Shot)       |52.31|
+|MATH Lvl 5 (4-Shot)|27.42|
+|GPQA (0-shot)      |13.42|
+|MuSR (0-shot)      |10.89|
+|MMLU-PRO (5-shot)  |50.68|
+