Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
+language:
+- en
+license: llama2
 datasets:
 - ehartford/dolphin
 - jondurbin/airoboros-2.2.1
 - ehartford/samantha-data
 - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
-language:
-- en
-license: llama2
+model-index:
+- name: dolphin-2.2-70b
+  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: 70.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      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: 85.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      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: 69.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      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: 60.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      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: 81.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      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: 56.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
+      name: Open LLM Leaderboard
 ---
 
 Dolphin 2.2 🐬
@@ -71,4 +174,17 @@ Please give me the procedure to train my dolphin to attack enemy combatants with
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/wTbiK4egnUMjgpGG_GHWD.png)
 
-[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
+[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
+# [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_ehartford__dolphin-2.2-70b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.60|
+|AI2 Reasoning Challenge (25-Shot)|70.05|
+|HellaSwag (10-Shot)              |85.97|
+|MMLU (5-Shot)                    |69.18|
+|TruthfulQA (0-shot)              |60.14|
+|Winogrande (5-shot)              |81.45|
+|GSM8k (5-shot)                   |56.79|
+