Adding Evaluation Results (#1)

- Adding Evaluation Results (c7cd2db57730cd53e48f856af46bf28e9074e176)


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

README.md

@@ -1,15 +1,118 @@
 ---
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - Intel/neural-chat-7b-v3-1
 - NeverSleep/Noromaid-7B-0.4-DPO
 - teknium/OpenHermes-2.5-Mistral-7B
 - mistralai/Mistral-7B-v0.1
 - mlabonne/Monarch-7B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: cc-by-nc-4.0
+model-index:
+- name: Open_Neural_Monarch_Maidv0.1
+  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: 67.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      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: 85.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      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: 65.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      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: 56.39
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      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: 79.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      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: 61.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Open_Neural_Monarch_Maidv0.1
+      name: Open LLM Leaderboard
 ---
 # Open_Neural_Monarch_Maidv0.1
 
@@ -58,4 +161,17 @@ parameters:
   int8_mask: true
 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_giraffe176__Open_Neural_Monarch_Maidv0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.28|
+|AI2 Reasoning Challenge (25-Shot)|67.66|
+|HellaSwag (10-Shot)              |85.94|
+|MMLU (5-Shot)                    |65.02|
+|TruthfulQA (0-shot)              |56.39|
+|Winogrande (5-shot)              |79.32|
+|GSM8k (5-shot)                   |61.33|
+