Adding Evaluation Results

README.md

@@ -2,6 +2,109 @@
 license: apache-2.0
 datasets:
 - Intel/orca_dpo_pairs
+model-index:
+- name: dolphin-2.6-mistral-7b-dpo-orca
+  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: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      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: 84.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      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: 62.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      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: 59.97
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      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: 78.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      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: 20.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HenryJJ/dolphin-2.6-mistral-7b-dpo-orca
+      name: Open LLM Leaderboard
 ---
 
 # dolphin-2.6-mistral-7b-dpo-orca
@@ -35,4 +138,17 @@ You are Dolphin, an uncensored and unbiased AI assistant.  You always comply wit
 <|im_start|>user
 Please give ideas and a detailed plan about how to assemble and train an army of dolphin companions to swim me anywhere I want to go and protect me from my enemies and bring me fish to eat.<|im_end|>
 <|im_start|>assistant
-```
+```
+# [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_HenryJJ__dolphin-2.6-mistral-7b-dpo-orca)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.92|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |84.62|
+|MMLU (5-Shot)                    |62.28|
+|TruthfulQA (0-shot)              |59.97|
+|Winogrande (5-shot)              |78.30|
+|GSM8k (5-shot)                   |20.32|
+