Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
-inference: false
+license: apache-2.0
 tags:
 - dare
 - super mario merge
 - pytorch
 - solar
 - merge
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: solar-megamerge-dare-10.7b-v1
+  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: 66.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      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: 85.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      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: 66.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      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: 54.33
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      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: 82.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      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: 58.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/solar-megamerge-dare-10.7b-v1
+      name: Open LLM Leaderboard
 ---
 
 # solar megamerge 10.7b
@@ -60,3 +163,17 @@ python3 hf_merge.py mergelist.yaml solar-1
 ### Notes
 
 * in the yaml: `p=weight` and `lambda=1/density`
+
+# [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_martyn__solar-megamerge-dare-10.7b-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.79|
+|AI2 Reasoning Challenge (25-Shot)|66.13|
+|HellaSwag (10-Shot)              |85.30|
+|MMLU (5-Shot)                    |66.03|
+|TruthfulQA (0-shot)              |54.33|
+|Winogrande (5-shot)              |82.95|
+|GSM8k (5-shot)                   |58.00|
+