Adding Evaluation Results (#1)

- Adding Evaluation Results (374807b4ac5729bfc545cbdb915c8717cfc3665a)


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

README.md

@@ -1,11 +1,106 @@
 ---
-base_model:
-- Qwen/Qwen2.5-7B
-- Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 tags:
 - mergekit
 - merge
+base_model:
+- Qwen/Qwen2.5-7B
+- Qwen/Qwen2.5-7B-Instruct
+model-index:
+- name: Qwen2.5-7B-della-test
+  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: 62.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      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: 36.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      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: 30.59
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      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: 8.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      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: 12.89
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      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: 38.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Etherll/Qwen2.5-7B-della-test
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -43,3 +138,17 @@ parameters:
 dtype: bfloat16
 
 ```
+
+# [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_Etherll__Qwen2.5-7B-della-test)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.83|
+|IFEval (0-Shot)    |62.95|
+|BBH (3-Shot)       |36.85|
+|MATH Lvl 5 (4-Shot)|30.59|
+|GPQA (0-shot)      | 8.95|
+|MuSR (0-shot)      |12.89|
+|MMLU-PRO (5-shot)  |38.75|
+