Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-base_model:
-- NeverSleep/Noromaid-7b-v0.2
-- NeuralNovel/Aeryth-7B-v0.1
+license: apache-2.0
+library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
-library_name: transformers
+base_model:
+- NeverSleep/Noromaid-7b-v0.2
+- NeuralNovel/Aeryth-7B-v0.1
 pipeline_tag: text-generation
+model-index:
+- name: Noromaid-Aeryth-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: 56.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-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: 78.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-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: 57.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-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: 65.66
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-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: 71.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-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: 16.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
+      name: Open LLM Leaderboard
 ---
 # Noromaid-Aeryth-7B
 
@@ -43,4 +146,17 @@ slices:
 - sources:
   - layer_range: [0, 32]
     model: NeuralNovel/Aeryth-7B-v0.1
-```
+```
+# [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_s3nh__Noromaid-Aeryth-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.82|
+|AI2 Reasoning Challenge (25-Shot)|56.74|
+|HellaSwag (10-Shot)              |78.62|
+|MMLU (5-Shot)                    |57.29|
+|TruthfulQA (0-shot)              |65.66|
+|Winogrande (5-shot)              |71.82|
+|GSM8k (5-shot)                   |16.76|
+