Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
 language:
 - eng
+license:
+- mit
 tags:
 - llama-2
 - sft
-license:
-- mit
 datasets:
 - LDJnr/Capybara
 - LDJnr/LessWrong-Amplify-Instruct
 - LDJnr/Pure-Dove
 - LDJnr/Verified-Camel
+model-index:
+- name: Nous-Capybara-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: 55.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-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: 80.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-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: 48.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-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: 51.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-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: 73.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-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: 6.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Nous-Capybara-7B
+      name: Open LLM Leaderboard
 ---
 
 ## **Nous-Capybara-7B V1**
@@ -117,4 +220,17 @@ The following are benchmarks we checked for contamination for:
   journal={arXiv preprint arXiv:(comming soon)},
   year={2023}
 }
-```
+```
+# [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_NousResearch__Nous-Capybara-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.70|
+|AI2 Reasoning Challenge (25-Shot)|55.29|
+|HellaSwag (10-Shot)              |80.73|
+|MMLU (5-Shot)                    |48.72|
+|TruthfulQA (0-shot)              |51.13|
+|Winogrande (5-shot)              |73.32|
+|GSM8k (5-shot)                   | 6.97|
+