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

@@ -1,5 +1,8 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
@@ -13,8 +16,6 @@ tags:
 - nerd
 - homer
 - Qandora
-language:
-- en
 base_model:
 - bunnycore/Qandora-2.5-7B-Creative
 - allknowingroger/HomerSlerp1-7B
@@ -23,7 +24,101 @@ base_model:
 - jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
 - newsbang/Homer-v0.5-Qwen2.5-7B
 pipeline_tag: text-generation
-library_name: transformers
+model-index:
+- name: Qwen2.5-7B-HomerAnvita-NerdMix
+  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: 77.08
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      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: 36.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      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: 29.53
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      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: 9.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      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: 14.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      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: 38.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
+      name: Open LLM Leaderboard
 ---
 
 # ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
@@ -205,4 +300,17 @@ This model is open-sourced under the **Apache-2.0 License**.
 - `jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0`
 - `newsbang/Homer-v0.5-Qwen2.5-7B`
 
----
+---
+# [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_ZeroXClem__Qwen2.5-7B-HomerAnvita-NerdMix)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.17|
+|IFEval (0-Shot)    |77.08|
+|BBH (3-Shot)       |36.58|
+|MATH Lvl 5 (4-Shot)|29.53|
+|GPQA (0-shot)      | 9.28|
+|MuSR (0-shot)      |14.41|
+|MMLU-PRO (5-shot)  |38.13|
+