Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 tags:
 - moe
 - merge
+model-index:
+- name: Cognito-2x7B-bf16
+  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: 72.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      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: 88.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      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: 64.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      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: 71.7
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      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: 85.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      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: 70.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Cognito-2x7B-bf16
+      name: Open LLM Leaderboard
 ---
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/YIxTRkaxXfPL9NHM6ZL76.jpeg)
@@ -55,4 +158,17 @@ If all our tokens are sent to just a few popular experts, that will make trainin
 
 
 ## "Wait...but you called this a frankenMoE?"
-The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
+The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
+# [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_Kquant03__Cognito-2x7B-bf16)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.74|
+|AI2 Reasoning Challenge (25-Shot)|72.95|
+|HellaSwag (10-Shot)              |88.96|
+|MMLU (5-Shot)                    |64.86|
+|TruthfulQA (0-shot)              |71.70|
+|Winogrande (5-shot)              |85.64|
+|GSM8k (5-shot)                   |70.36|
+