Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-license: apache-2.0
-datasets:
-- argilla/distilabel-intel-orca-dpo-pairs
 language:
 - en
+license: apache-2.0
 tags:
 - distilabel
 - dpo
 - rlaif
 - rlhf
+datasets:
+- argilla/distilabel-intel-orca-dpo-pairs
+model-index:
+- name: distilabeled-Hermes-2.5-Mistral-7B
+  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: 66.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      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: 85.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      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: 63.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      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: 55.75
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      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: 78.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      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: 60.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/distilabeled-Hermes-2.5-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 # ⚗️ distilabeled OpenHermes 2.5 Mistral 7B
 
@@ -146,3 +249,17 @@ We'd like to thank the amazing open community and in particular:
 * 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-Hermes-2.5-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.42|
+|AI2 Reasoning Challenge (25-Shot)|66.30|
+|HellaSwag (10-Shot)              |85.15|
+|MMLU (5-Shot)                    |63.50|
+|TruthfulQA (0-shot)              |55.75|
+|Winogrande (5-shot)              |78.93|
+|GSM8k (5-shot)                   |60.88|
+