Adding Evaluation Results

README.md

@@ -1,10 +1,105 @@
 ---
-license: creativeml-openrail-m
 language:
 - fr
 - en
+license: creativeml-openrail-m
 tags:
 - chatml
+model-index:
+- name: EnnoAi-Pro-Llama-3-8B
+  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: 31.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      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: 17.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      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: 0.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      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: 1.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      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: 9.08
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      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: 12.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-Llama-3-8B
+      name: Open LLM Leaderboard
 ---
 # French Pro model
 This version aims to be a multilingual model (EN 🇺🇸 + FR 🇫🇷) to refine the specific professional tasks in French.
@@ -28,4 +123,17 @@ We use the default ChatML format with `system` role support.
 {ASSISTANT_ENTRY}<|im_end|>
 ```
 
-**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)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.17|
+|IFEval (0-Shot)    |31.95|
+|BBH (3-Shot)       |17.51|
+|MATH Lvl 5 (4-Shot)| 0.15|
+|GPQA (0-shot)      | 1.57|
+|MuSR (0-shot)      | 9.08|
+|MMLU-PRO (5-shot)  |12.79|
+