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
 - mixtral
 - merge
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: mixtral-megamerge-dare-8x7b-v2
+  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: 66.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      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: 86.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      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: 69.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      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: 53.81
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      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: 79.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      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: 53.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mixtral-megamerge-dare-8x7b-v2
+      name: Open LLM Leaderboard
 ---
 
 # mixtral megamerge 8x7b v2
@@ -37,3 +140,17 @@ python3 hf_merge.py to_merge_mixtral2.txt mixtral-2 -p 0.15 -lambda 1.95
 
 * MoE gates were filtered for compatibility then averaged with `(tensor1 + tensor2)/2`
 * seems to generalize prompting formats and sampling settings
+
+# [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__mixtral-megamerge-dare-8x7b-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.20|
+|AI2 Reasoning Challenge (25-Shot)|66.47|
+|HellaSwag (10-Shot)              |86.11|
+|MMLU (5-Shot)                    |69.14|
+|TruthfulQA (0-shot)              |53.81|
+|Winogrande (5-shot)              |79.79|
+|GSM8k (5-shot)                   |53.90|
+