Adding Evaluation Results

README.md

@@ -1,6 +1,3 @@
-
-
-
 ---
 base_model:
 - rombodawg/Rombos-LLM-V2.5-Qwen-7b
@@ -13,7 +10,105 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+model-index:
+- name: Qwen2.5-Dyanka-7B-Preview
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 76.4
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 36.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 48.79
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      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#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      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: 15.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      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: 37.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview
+      name: Open LLM Leaderboard
 ---
 
 ![Qwen2.5-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview/resolve/main/Costume1(62).png)
@@ -72,3 +167,18 @@ parameters:
   int8_mask: true
 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/Xiaojian9992024__Qwen2.5-Dyanka-7B-Preview-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Xiaojian9992024%2FQwen2.5-Dyanka-7B-Preview&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    37.30|
+|IFEval (0-Shot)    |    76.40|
+|BBH (3-Shot)       |    36.62|
+|MATH Lvl 5 (4-Shot)|    48.79|
+|GPQA (0-shot)      |     8.95|
+|MuSR (0-shot)      |    15.51|
+|MMLU-PRO (5-shot)  |    37.51|
+