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

@@ -1,9 +1,7 @@
 ---
-base_model:
-- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
-- yam-peleg/Experiment26-7B
-- liminerity/M7-7b
-- LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
+language:
+- en
+license: openrail
 library_name: transformers
 tags:
 - chemistry
@@ -15,9 +13,106 @@ tags:
 - finance
 - legal
 - medical
-license: openrail
-language:
-- en
+base_model:
+- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+- yam-peleg/Experiment26-7B
+- liminerity/M7-7b
+- LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
+model-index:
+- name: LCARS_TOP_SCORE
+  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: 43.71
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      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: 31.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      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: 6.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      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: 4.81
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      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: 12.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      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: 22.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_TOP_SCORE
+      name: Open LLM Leaderboard
 ---
 
 Used as the Boss of Other Agents!
@@ -64,3 +159,17 @@ VERY GOOD MODEL !!!!! (HIGH SCORES) - 78.9 Average
   url          = {https://doi.org/10.5281/zenodo.5371628},
 }
 
+
+# [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/LeroyDyer__LCARS_TOP_SCORE-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.32|
+|IFEval (0-Shot)    |43.71|
+|BBH (3-Shot)       |31.70|
+|MATH Lvl 5 (4-Shot)| 6.72|
+|GPQA (0-shot)      | 4.81|
+|MuSR (0-shot)      |12.43|
+|MMLU-PRO (5-shot)  |22.57|
+