Adding Evaluation Results (#1)

- Adding Evaluation Results (f7c68efc325d3ee099ad3b697f04faa1395ae7a2)

README.md

@@ -1,4 +1,8 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 base_model:
 - ResplendentAI/Paradigm_7B
 - jeiku/Theory_of_Mind_Mistral
@@ -7,10 +11,109 @@ base_model:
 - ResplendentAI/Paradigm_7B
 - jeiku/Gnosis_Reformatted_Mistral
 - ResplendentAI/Paradigm_7B
-library_name: transformers
-license: apache-2.0
-language:
-- en
+model-index:
+- name: Aura_v2_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: 73.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_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: 88.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_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: 63.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_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: 75.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_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: 84.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_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: 66.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Aura_v2_7B
+      name: Open LLM Leaderboard
 ---
 # Aura v2
 
@@ -24,4 +127,17 @@ If you have trouble getting the model to follow an asterisks/quote format, I rec
 
 This model responds best to ChatML for multiturn conversations.
 
-This model, like all other Mistral based models, is compatible with a Mistral compatible mmproj file for multimodal vision capabilities in KoboldCPP.
+This model, like all other Mistral based models, is compatible with a Mistral compatible mmproj file for multimodal vision capabilities in KoboldCPP.
+# [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_ResplendentAI__Aura_v2_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.36|
+|AI2 Reasoning Challenge (25-Shot)|73.46|
+|HellaSwag (10-Shot)              |88.64|
+|MMLU (5-Shot)                    |63.97|
+|TruthfulQA (0-shot)              |75.17|
+|Winogrande (5-shot)              |84.45|
+|GSM8k (5-shot)                   |66.49|
+