Adding Evaluation Results (#3)

- Adding Evaluation Results (7ce04b0754aab056e9e84202dc1b9f068fe05531)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,10 +1,113 @@
 ---
+license: apache-2.0
 library_name: transformers
 tags:
 - conversational
-license: apache-2.0
 datasets:
 - Locutusque/hyperion-v1.5
+model-index:
+- name: Hyperion-1.5-Mistral-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: 60.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-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: 83.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-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: 63.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-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: 41.78
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-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: 78.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-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: 40.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hyperion-1.5-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 # Model Card for Locutusque/Hyperion-1.5-Mistral-7B
 
@@ -72,4 +175,17 @@ If you use Locutusque/Hyperion-1.5-Mistral-7B in your research, please cite the
 
 ## Quants
 
-exl2 and GGUF by bartowski - https://huggingface.co/bartowski/Hyperion-1.5-Mistral-7B-exl2 https://huggingface.co/bartowski/Hyperion-1.5-Mistral-7B-GGUF
+exl2 and GGUF by bartowski - https://huggingface.co/bartowski/Hyperion-1.5-Mistral-7B-exl2 https://huggingface.co/bartowski/Hyperion-1.5-Mistral-7B-GGUF
+# [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_Locutusque__Hyperion-1.5-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.43|
+|AI2 Reasoning Challenge (25-Shot)|60.49|
+|HellaSwag (10-Shot)              |83.64|
+|MMLU (5-Shot)                    |63.57|
+|TruthfulQA (0-shot)              |41.78|
+|Winogrande (5-shot)              |78.61|
+|GSM8k (5-shot)                   |40.49|
+