Adding Evaluation Results (#2)

- Adding Evaluation Results (33f3d78ca96682b0cc955bfe1f6d3a1b676680c7)


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

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- mistralai/Mistral-7B-Instruct-v0.2
-- mistralai/Mistral-7B-Instruct-v0.1
+license: apache-2.0
 tags:
 - mergekit
 - merge
 - moe
-license: apache-2.0
+base_model:
+- mistralai/Mistral-7B-Instruct-v0.2
+- mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: mistral-instruct-moe-experimental
+  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: 61.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      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: 81.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      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: 58.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      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: 60.4
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      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: 76.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      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: 31.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental
+      name: Open LLM Leaderboard
 ---
 # Mistral Instruct MoE experimental
 
@@ -41,4 +144,17 @@ experts:
     positive_prompts: [""]
   - source_model: mistralai/Mistral-7B-Instruct-v0.1
     positive_prompts: [""]
-```
+```
+# [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_osanseviero__mistral-instruct-moe-experimental)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.39|
+|AI2 Reasoning Challenge (25-Shot)|61.01|
+|HellaSwag (10-Shot)              |81.55|
+|MMLU (5-Shot)                    |58.22|
+|TruthfulQA (0-shot)              |60.40|
+|Winogrande (5-shot)              |76.09|
+|GSM8k (5-shot)                   |31.08|
+