Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
+license: apache-2.0
+tags:
+- mergekit
+- merge
 base_model:
 - openchat/openchat-3.5-0106
 - mistralai/Mistral-7B-Instruct-v0.2
 - Open-Orca/Mistral-7B-OpenOrca
 - WizardLM/WizardMath-7B-V1.1
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: DARE-Merging
+  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: 25.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      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: 26.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      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: 23.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      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: 48.31
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      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: 51.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      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: 0.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/DARE-Merging
+      name: Open LLM Leaderboard
 ---
 # result
 
@@ -50,4 +153,17 @@ base_model: mistralai/Mistral-7B-Instruct-v0.2
 parameters:
   normalize: true
 dtype: float16
-```
+```
+# [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_Cartinoe5930__DARE-Merging)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.19|
+|AI2 Reasoning Challenge (25-Shot)|25.26|
+|HellaSwag (10-Shot)              |26.11|
+|MMLU (5-Shot)                    |23.68|
+|TruthfulQA (0-shot)              |48.31|
+|Winogrande (5-shot)              |51.70|
+|GSM8k (5-shot)                   | 0.08|
+