Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-license: llama2
-inference: true 
 language:
 - fr
+license: llama2
 tags:
 - pytorch
 - code
+inference: true
+model-index:
+- name: ARIA-70B-French
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 64.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 85.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 52.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 80.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 26.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=willyninja30/ARIA-70B-French
+      name: Open LLM Leaderboard
 ---
 # ARIA French is a model created from llama 2 70B finetuned on a french dataset.
 
@@ -42,4 +145,17 @@ Output : Models generate text only.
 
 # Model Architecture : ARIA is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
 
-License : A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/
+License : A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_willyninja30__ARIA-70B-French)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.37|
+|AI2 Reasoning Challenge (25-Shot)|64.51|
+|HellaSwag (10-Shot)              |85.87|
+|MMLU (5-Shot)                    |63.88|
+|TruthfulQA (0-shot)              |52.80|
+|Winogrande (5-shot)              |80.51|
+|GSM8k (5-shot)                   |26.69|
+