Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 datasets:
 - teknium/openhermes
 - argilla/ultrafeedback-binarized-preferences
 - Intel/orca_dpo_pairs
-language:
-- en
-library_name: transformers
+model-index:
+- name: DPOpenHermes-11B
+  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: 66.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      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: 84.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      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: 64.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      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: 57.34
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      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: 76.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      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: 51.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openaccess-ai-collective/DPOpenHermes-11B
+      name: Open LLM Leaderboard
 ---
 # DPOpenHermes 11B
 
@@ -23,4 +126,17 @@ slices:
       layer_range: [8, 32]
 merge_method: passthrough
 dtype: bfloat16
-```
+```
+# [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_openaccess-ai-collective__DPOpenHermes-11B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.83|
+|AI2 Reasoning Challenge (25-Shot)|66.55|
+|HellaSwag (10-Shot)              |84.80|
+|MMLU (5-Shot)                    |64.02|
+|TruthfulQA (0-shot)              |57.34|
+|Winogrande (5-shot)              |76.95|
+|GSM8k (5-shot)                   |51.33|
+