Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
-library_name: transformers
 license: other
+library_name: transformers
 license_name: gemma-terms-of-use
 license_link: https://ai.google.dev/gemma/terms
+model-index:
+- name: Gemma-Wukong-2b
+  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: 45.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      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: 66.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      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: 38.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      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: 44.29
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      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: 62.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      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: 9.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=RESMPDEV/Gemma-Wukong-2b
+      name: Open LLM Leaderboard
 ---
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/xOe1Nb3S9Nb53us7_Ja3s.jpeg)
 
@@ -454,4 +557,17 @@ AI development compared to similarly sized models.
 
 Using the benchmark evaluation metrics described in this document, these models
 have shown to provide superior performance to other, comparably-sized open model
-alternatives.
+alternatives.
+# [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_RESMPDEV__Gemma-Wukong-2b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.64|
+|AI2 Reasoning Challenge (25-Shot)|45.90|
+|HellaSwag (10-Shot)              |66.83|
+|MMLU (5-Shot)                    |38.01|
+|TruthfulQA (0-shot)              |44.29|
+|Winogrande (5-shot)              |62.98|
+|GSM8k (5-shot)                   | 9.86|
+