Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,14 +1,109 @@
 ---
-license: llama3.1
-library_name: transformers
-datasets:
-- Locutusque/hercules-v6.1
 language:
 - en
 - zh
-pipeline_tag: text-generation
+license: llama3.1
+library_name: transformers
 tags:
 - not-for-all-audiences
+datasets:
+- Locutusque/hercules-v6.1
+pipeline_tag: text-generation
+model-index:
+- name: Hercules-6.1-Llama-3.1-8B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 60.07
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 24.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 15.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 1.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 29.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Hercules-6.1-Llama-3.1-8B
+      name: Open LLM Leaderboard
 ---
 # Model Card: Locutusque/Hercules-6.1-Llama-3.1-8B
 
@@ -69,3 +164,17 @@ Hercules-6.1-Llama-3.1-8B is well-suited to the following applications:
 |gsm8k                            |    3.0|flexible-extract|     5|exact_match      |↑  | 0.7801|±  |0.0114|
 |                                 |       |strict-match    |     5|exact_match      |↑  | 0.7809|±  |0.0114|
 |truthfulqa_mc2                   |    2.0|none            |     0|acc              |↑  | 0.5389|±  |0.0150|
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__Hercules-6.1-Llama-3.1-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.40|
+|IFEval (0-Shot)    |60.07|
+|BBH (3-Shot)       |24.15|
+|MATH Lvl 5 (4-Shot)|15.63|
+|GPQA (0-shot)      | 1.45|
+|MuSR (0-shot)      | 3.42|
+|MMLU-PRO (5-shot)  |29.65|
+