Adding Evaluation Results (#1)

- Adding Evaluation Results (75836afd19602f6e18d8069fd2552b26f74cbbaf)

README.md

@@ -1,18 +1,113 @@
 ---
+language:
+- en
+- zh
 license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
 - lazymergekit
 - Locutusque/StockQwen-2.5-7B
 - allknowingroger/QwenSlerp8-7B
-language:
-- en
-- zh
 base_model:
 - allknowingroger/QwenSlerp8-7B
 - Locutusque/StockQwen-2.5-7B
-library_name: transformers
+model-index:
+- name: Qwen-2.5-Aether-SlerpFusion-7B
+  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: 62.62
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      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: 36.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      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: 24.17
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      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: 6.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      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: 11.29
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      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: 36.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
+      name: Open LLM Leaderboard
 ---
 
 # ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
@@ -125,4 +220,17 @@ This model is open-sourced under the **Apache-2.0 License**.
 - `Locutusque/StockQwen-2.5-7B`
 - `allknowingroger/QwenSlerp8-7B`
 
----
+---
+# [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__Qwen-2.5-Aether-SlerpFusion-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.59|
+|IFEval (0-Shot)    |62.62|
+|BBH (3-Shot)       |36.01|
+|MATH Lvl 5 (4-Shot)|24.17|
+|GPQA (0-shot)      | 6.49|
+|MuSR (0-shot)      |11.29|
+|MMLU-PRO (5-shot)  |36.96|
+