Adding Evaluation Results

README.md

@@ -1,8 +1,103 @@
 ---
-license: creativeml-openrail-m
 language:
 - fr
 - en
+license: creativeml-openrail-m
+model-index:
+- name: EnnoAi-Pro-Llama-3-8B-v0.3
+  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: 50.83
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      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: 16.67
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      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: 1.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      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: 2.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      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: 12.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      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: 22.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.3
+      name: Open LLM Leaderboard
 ---
 # Alpha version for the French Pro model
 Suitable model for professional use
@@ -13,4 +108,17 @@ Selected French professional dataset
 # Tuning
 Use specific receipices with QLora methods
 
-**This model is under construction**
+**This model is under construction**
+# [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_Enno-Ai__EnnoAi-Pro-Llama-3-8B-v0.3)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.50|
+|IFEval (0-Shot)    |50.83|
+|BBH (3-Shot)       |16.67|
+|MATH Lvl 5 (4-Shot)| 1.06|
+|GPQA (0-shot)      | 2.01|
+|MuSR (0-shot)      |12.31|
+|MMLU-PRO (5-shot)  |22.12|
+