Adding Evaluation Results (#1)

- Adding Evaluation Results (d7bce76d5cd44598094f1c452729d0f672977107)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,116 @@
 ---
-base_model:
-- grimjim/Mistral-Starling-merge-trial1-7B
-- grimjim/kukulemon-7B
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: cc-by-nc-4.0
+base_model:
+- grimjim/Mistral-Starling-merge-trial1-7B
+- grimjim/kukulemon-7B
 pipeline_tag: text-generation
+model-index:
+- name: cuckoo-starling-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: 66.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-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: 85.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-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: 64.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-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: 59.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-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: 80.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-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: 62.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/cuckoo-starling-7B
+      name: Open LLM Leaderboard
 ---
 # cuckoo-starling-32k-7B
 
@@ -56,3 +159,17 @@ parameters:
 dtype: bfloat16
 
 ```
+
+# [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_grimjim__cuckoo-starling-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.93|
+|AI2 Reasoning Challenge (25-Shot)|66.81|
+|HellaSwag (10-Shot)              |85.97|
+|MMLU (5-Shot)                    |64.88|
+|TruthfulQA (0-shot)              |59.03|
+|Winogrande (5-shot)              |80.11|
+|GSM8k (5-shot)                   |62.77|
+