Adding Evaluation Results

README.md

@@ -1,15 +1,117 @@
 ---
-thumbnail: >-
-  https://cdn-uploads.huggingface.co/production/uploads/62fb1ef7e8c9c532aa7d19e4/NswB5XPkkOljeRh1xbMmR.png
-pipeline_tag: text-generation
-license: llama2
 language:
 - en
+license: llama2
 library_name: transformers
 tags:
 - Riiid
 - llama-2
 - sheep-duck-llama-2
+thumbnail: https://cdn-uploads.huggingface.co/production/uploads/62fb1ef7e8c9c532aa7d19e4/NswB5XPkkOljeRh1xbMmR.png
+pipeline_tag: text-generation
+model-index:
+- name: sheep-duck-llama-2-70b-v1.1
+  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: 73.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      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: 87.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      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: 70.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      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: 64.55
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      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: 83.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      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: 47.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Riiid/sheep-duck-llama-2-70b-v1.1
+      name: Open LLM Leaderboard
 ---
 
 # sheep-duck-llama-2
@@ -114,4 +216,17 @@ Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams,
 Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
   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_Riiid__sheep-duck-llama-2-70b-v1.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.22|
+|AI2 Reasoning Challenge (25-Shot)|73.12|
+|HellaSwag (10-Shot)              |87.77|
+|MMLU (5-Shot)                    |70.77|
+|TruthfulQA (0-shot)              |64.55|
+|Winogrande (5-shot)              |83.11|
+|GSM8k (5-shot)                   |47.99|
+