Adding Evaluation Results (#1)

- Adding Evaluation Results (68e2c89affc2e33b6406f91068e0330d073cba7d)


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

README.md

@@ -1,10 +1,113 @@
 ---
+language:
+- en
+license: apache-2.0
 tags:
 - mistral
 - merge
-license: apache-2.0
-language:
-- en
+model-index:
+- name: macaroni-7b
+  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: 73.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      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: 88.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      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: 64.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      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: 68.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      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: 84.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      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: 68.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/macaroni-7b
+      name: Open LLM Leaderboard
 ---
 # Macaroni 7B
 
@@ -26,3 +129,17 @@ This is an experimental merge of pre-trained mistral language models with fblgit
   * Ethical Use: Users are encouraged to use The Model ethically and responsibly. The creator(s) disclaim any responsibility for misuse or unethical use of The Model.
 
   * Modifications: Any modifications made to The Model by third parties are the sole responsibility of the party making the modifications. The original creator(s) of The Model shall not be responsible for any modifications made by third parties.
+
+# [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_andrijdavid__macaroni-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.60|
+|AI2 Reasoning Challenge (25-Shot)|73.12|
+|HellaSwag (10-Shot)              |88.17|
+|MMLU (5-Shot)                    |64.58|
+|TruthfulQA (0-shot)              |68.76|
+|Winogrande (5-shot)              |84.37|
+|GSM8k (5-shot)                   |68.61|
+