Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
-license: apache-2.0
-datasets:
-  - argilla/distilabel-intel-orca-dpo-pairs
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - distilabel
-  - dpo
-  - rlaif
-  - rlhf
-  - merge
-  - mergekit
+- distilabel
+- dpo
+- rlaif
+- rlhf
+- merge
+- mergekit
+datasets:
+- argilla/distilabel-intel-orca-dpo-pairs
+model-index:
+- name: distilabeled-Marcoro14-7B-slerp-full
+  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: 70.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      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: 87.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      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: 65.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      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: 64.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      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: 82.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      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: 70.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Marcoro14-7B-slerp-full
+      name: Open LLM Leaderboard
 ---
 # ⚗️ distilabeled Marcoro14 7B Slerp
 
@@ -75,3 +178,17 @@ We'd like to thank the amazing open community and in particular:
 * The Intel team for publishing a great open dataset and show how well it worked in the first place 
 * Teknium and NousResearch for their awesome work and models.
 * Maxime for sharing such great resources.
+
+# [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_argilla__distilabeled-Marcoro14-7B-slerp-full)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.40|
+|AI2 Reasoning Challenge (25-Shot)|70.65|
+|HellaSwag (10-Shot)              |87.55|
+|MMLU (5-Shot)                    |65.33|
+|TruthfulQA (0-shot)              |64.21|
+|Winogrande (5-shot)              |82.00|
+|GSM8k (5-shot)                   |70.66|
+