Adding Evaluation Results (#1)

- Adding Evaluation Results (1232987ee78d8478256ba14b78bbbef93ff7c113)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,10 +1,105 @@
 ---
+license: other
 library_name: transformers
 base_model:
 - Qwen/Qwen2.5-72B-Instruct
-license: other
 license_name: qwen
 license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+model-index:
+- name: Replete-LLM-V2.5-Qwen-72b_Duplicated
+  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: 71.55
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      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: 61.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      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: 47.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      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: 19.8
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      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: 17.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      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: 54.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
 ---
 # Rombos-LLM-V2.5-Qwen-72b
 
@@ -21,3 +116,17 @@ GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-72b-GGUF
 EXL2: 
 
 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_rombodawg__Replete-LLM-V2.5-Qwen-72b_Duplicated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |45.39|
+|IFEval (0-Shot)    |71.55|
+|BBH (3-Shot)       |61.27|
+|MATH Lvl 5 (4-Shot)|47.58|
+|GPQA (0-shot)      |19.80|
+|MuSR (0-shot)      |17.32|
+|MMLU-PRO (5-shot)  |54.83|
+