Adding Evaluation Results (#4)

- Adding Evaluation Results (1b3b4e915ca09feb31bdb823a93a59e68050d2f0)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,14 +1,117 @@
 ---
-library_name: transformers
 license: apache-2.0
-datasets:
-- Locutusque/Hercules-v3.0
+library_name: transformers
 tags:
 - chemistry
 - biology
 - code
 - medical
 - not-for-all-audiences
+datasets:
+- Locutusque/Hercules-v3.0
+model-index:
+- name: Hercules-3.1-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: 61.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-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: 83.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-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: 63.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-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: 42.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-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: 79.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-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: 42.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 # Model Card: Hercules-3.1-Mistral-7B
 
@@ -82,4 +185,17 @@ This model was fine-tuned using the TPU-Alignment repository. https://github.com
 
 # Quants
 
-ExLlamaV2 by bartowski https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-exl2
+ExLlamaV2 by bartowski https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-exl2
+# [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__Hercules-3.1-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.09|
+|AI2 Reasoning Challenge (25-Shot)|61.18|
+|HellaSwag (10-Shot)              |83.55|
+|MMLU (5-Shot)                    |63.65|
+|TruthfulQA (0-shot)              |42.83|
+|Winogrande (5-shot)              |79.01|
+|GSM8k (5-shot)                   |42.30|
+