Adding Evaluation Results (#5)

- Adding Evaluation Results (a61126f5d4ca0f9b6a75ec704468b976509ebb11)


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

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - medical
@@ -6,12 +9,112 @@ tags:
 - biology
 - chemistry
 - not-for-all-audiences
-license: apache-2.0
+base_model: alpindale/Mistral-7B-v0.2-hf
 datasets:
 - Locutusque/hercules-v4.0
-language:
-- en
-base_model: alpindale/Mistral-7B-v0.2-hf
+model-index:
+- name: Hercules-4.0-Mistral-v0.2-7B
+  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: 58.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      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: 82.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      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: 62.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      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: 40.99
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      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: 45.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-4.0-Mistral-v0.2-7B
+      name: Open LLM Leaderboard
 ---
 # Model Card: Hercules-4.0-Mistral-v0.2-7B
 
@@ -94,4 +197,17 @@ This model was fine-tuned using my TPU-Alignment repository. https://github.com/
 | - mmlu_flan_cot_fewshot_social_sciences|N/A    |get-answer|     0|exact_match|0.6528|±  |0.0248|
 | - mmlu_flan_cot_fewshot_stem           |N/A    |get-answer|     0|exact_match|0.4925|±  |0.0266|
 |ai2_arc                                 |N/A    |none      |     0|acc        |0.6936|±  |0.0073|
-|                                        |       |none      |     0|acc_norm   |0.6984|±  |0.0074|
+|                                        |       |none      |     0|acc_norm   |0.6984|±  |0.0074|
+# [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-4.0-Mistral-v0.2-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.53|
+|AI2 Reasoning Challenge (25-Shot)|58.96|
+|HellaSwag (10-Shot)              |82.60|
+|MMLU (5-Shot)                    |62.66|
+|TruthfulQA (0-shot)              |40.99|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |45.41|
+