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

@@ -1,8 +1,103 @@
 ---
+license: apache-2.0
 library_name: transformers
 base_model:
 - Qwen/Qwen2.5-14B-Instruct
-license: apache-2.0
+model-index:
+- name: Replete-LLM-V2.5-Qwen-14b
+  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: 58.4
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      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: 49.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      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=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      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: 16.22
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      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: 18.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      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: 48.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
+      name: Open LLM Leaderboard
 ---
 # Replete-LLM-V2.5-Qwen-14b
 
@@ -18,4 +113,17 @@ GGUF:
 
 EXL2: 
 
-Benchmarks: (Coming soon)
+Benchmarks: (Coming soon)
+# [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_Replete-AI__Replete-LLM-V2.5-Qwen-14b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.52|
+|IFEval (0-Shot)    |58.40|
+|BBH (3-Shot)       |49.39|
+|MATH Lvl 5 (4-Shot)|15.63|
+|GPQA (0-shot)      |16.22|
+|MuSR (0-shot)      |18.83|
+|MMLU-PRO (5-shot)  |48.62|
+