Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
----
-license: creativeml-openrail-m
-language:
-- fr
-- en
-tags:
-- chatml
----
+---
+language:
+- fr
+- en
+license: creativeml-openrail-m
+tags:
+- chatml
+model-index:
+- name: EnnoAi-Pro-French-Llama-3-8B-v0.4
+  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: 41.89
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      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: 16.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      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: 0.6
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      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: 2.8
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      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: 10.76
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      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: 18.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Enno-Ai/EnnoAi-Pro-French-Llama-3-8B-v0.4
+      name: Open LLM Leaderboard
+---
 # Alpha version for the French Pro model
 Suitable model for professional use
 
@@ -15,4 +110,17 @@ 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-French-Llama-3-8B-v0.4)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |15.18|
+|IFEval (0-Shot)    |41.89|
+|BBH (3-Shot)       |16.88|
+|MATH Lvl 5 (4-Shot)| 0.60|
+|GPQA (0-shot)      | 2.80|
+|MuSR (0-shot)      |10.76|
+|MMLU-PRO (5-shot)  |18.16|
+