Adding Evaluation Results (#1)

- Adding Evaluation Results (812003aa276275984d5013bcb7d6474856cf119c)


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

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- brucethemoose/Yi-34B-200K-DARE-megamerge-v8
-- one-man-army/UNA-34Beagles-32K-bf16-v1
+license: apache-2.0
 tags:
 - mergekit
 - merge
 - Etheria
-license: apache-2.0
+base_model:
+- brucethemoose/Yi-34B-200K-DARE-megamerge-v8
+- one-man-army/UNA-34Beagles-32K-bf16-v1
+model-index:
+- name: VerB-Etheria-55b
+  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: 65.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      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: 81.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      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: 73.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      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: 57.52
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      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: 75.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      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: 28.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/VerB-Etheria-55b
+      name: Open LLM Leaderboard
 ---
 # VerB-Etheria-55b
 
@@ -56,4 +159,17 @@ slices:
       layer_range: [45, 59]
 merge_method: passthrough
 
-```
+```
+# [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_Steelskull__VerB-Etheria-55b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.83|
+|AI2 Reasoning Challenge (25-Shot)|65.96|
+|HellaSwag (10-Shot)              |81.48|
+|MMLU (5-Shot)                    |73.78|
+|TruthfulQA (0-shot)              |57.52|
+|Winogrande (5-shot)              |75.45|
+|GSM8k (5-shot)                   |28.81|
+