Adding Evaluation Results (#3)

- Adding Evaluation Results (9e7c86f9ea6be11ecd0fabc9b492a9d49af4135f)


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

README.md

@@ -1,16 +1,119 @@
 ---
 license: apache-2.0
 library_name: transformers
-base_model: mistralai/Mistral-7B-v0.1
 tags:
 - not-for-all-audiences
 - chemistry
 - math
 - code
 - physics
+base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - Locutusque/hercules-v2.0
 - Locutusque/hercules-v2.5
+model-index:
+- name: Hercules-2.5-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: 62.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-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: 83.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-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: 63.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-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: 43.44
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-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: 79.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-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: 49.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 # Model Card: Hercules-2.5-Mistral-7B
 
@@ -90,4 +193,17 @@ This model was fine-tuned using the TPU-Alignment repository. https://github.com
 
 # Quants
 
-exl2 by @bartowski https://huggingface.co/bartowski/Hercules-2.5-Mistral-7B-exl2
+exl2 by @bartowski https://huggingface.co/bartowski/Hercules-2.5-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-2.5-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.59|
+|AI2 Reasoning Challenge (25-Shot)|62.03|
+|HellaSwag (10-Shot)              |83.79|
+|MMLU (5-Shot)                    |63.49|
+|TruthfulQA (0-shot)              |43.44|
+|Winogrande (5-shot)              |79.72|
+|GSM8k (5-shot)                   |49.05|
+