Adding Evaluation Results

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+license: apache-2.0
 datasets:
 - ehartford/dolphin
 - jondurbin/airoboros-2.2.1
@@ -7,9 +10,109 @@ datasets:
 - ise-uiuc/Magicoder-OSS-Instruct-75K
 - ise-uiuc/Magicoder-Evol-Instruct-110K
 - LDJnr/Capybara
-language:
-- en
-license: apache-2.0
+model-index:
+- name: dolphin-2.6-mistral-7b-dpo-laser
+  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=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      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: 85.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      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: 63.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      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: 61.71
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      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: 79.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      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: 47.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
+      name: Open LLM Leaderboard
 ---
 
 Dolphin 2.6 Mistral 7b - DPO Laser 🐬
@@ -104,4 +207,17 @@ Dolphin 3.0 dataset is in progress, and will include:
 
 [If you would like to financially support my efforts](https://ko-fi.com/erichartford)
 
-[swag](https://fa7113.myshopify.com/)
+[swag](https://fa7113.myshopify.com/)
+# [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_cognitivecomputations__dolphin-2.6-mistral-7b-dpo-laser)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.28|
+|AI2 Reasoning Challenge (25-Shot)|66.30|
+|HellaSwag (10-Shot)              |85.73|
+|MMLU (5-Shot)                    |63.16|
+|TruthfulQA (0-shot)              |61.71|
+|Winogrande (5-shot)              |79.16|
+|GSM8k (5-shot)                   |47.61|
+