Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - jeiku/Cookie_7B
 - jeiku/SpaghettiOs_7B
 - jeiku/Rainbow_69_7B
 - jeiku/Paranoid_Android_7B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: other
+model-index:
+- name: NarrativeNexus_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: 66.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_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: 85.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_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: 63.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_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: 63.95
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_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: 79.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_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: 51.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
+      name: Open LLM Leaderboard
 ---
 # Nexus
 
@@ -53,4 +156,17 @@ models:
       weight: 0.75            
 dtype: float16
 
-```
+```
+# [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_jeiku__NarrativeNexus_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.30|
+|AI2 Reasoning Challenge (25-Shot)|66.13|
+|HellaSwag (10-Shot)              |85.74|
+|MMLU (5-Shot)                    |63.17|
+|TruthfulQA (0-shot)              |63.95|
+|Winogrande (5-shot)              |79.01|
+|GSM8k (5-shot)                   |51.78|
+