Adding Evaluation Results

This is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- Test157t/Hex-Macaroniac-7b
-- Test157t/Cetus-Sea-7b-128k
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: other
+base_model:
+- Test157t/Hex-Macaroniac-7b
+- Test157t/Cetus-Sea-7b-128k
+model-index:
+- name: Echidna-7b-128k
+  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=Test157t/Echidna-7b-128k
+      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: 85.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
+      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: 63.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
+      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: 56.07
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
+      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: 80.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
+      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: 56.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/yAUStIqYEyDeS6sUUkkCL.png)
 
@@ -133,3 +236,17 @@ dtype: bfloat16
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+
+# [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_Test157t__Echidna-7b-128k)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.88|
+|AI2 Reasoning Challenge (25-Shot)|66.13|
+|HellaSwag (10-Shot)              |85.18|
+|MMLU (5-Shot)                    |63.04|
+|TruthfulQA (0-shot)              |56.07|
+|Winogrande (5-shot)              |80.03|
+|GSM8k (5-shot)                   |56.86|
+