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

@@ -1,12 +1,6 @@
 ---
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
-- fblgit/cybertron-v4-qw7B-MGS
-- huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3
-- FreedomIntelligence/HuatuoGPT-o1-7B
-- rombodawg/Rombos-LLM-V2.5-Qwen-7b
 tags:
 - mergekit
 - merge
@@ -17,6 +11,107 @@ tags:
 - boolean-expression-champion
 - math-avoider
 - object-counting-struggler
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+- fblgit/cybertron-v4-qw7B-MGS
+- huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3
+- FreedomIntelligence/HuatuoGPT-o1-7B
+- rombodawg/Rombos-LLM-V2.5-Qwen-7b
+model-index:
+- name: Qwen2.5-THREADRIPPER-Small
+  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: 76.89
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      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: 35.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      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: 47.36
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      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: 8.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      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: 13.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      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: 37.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Xiaojian9992024/Qwen2.5-THREADRIPPER-Small
+      name: Open LLM Leaderboard
 ---
 base_model:
 - fblgit/cybertron-v4-qw7B-MGS
@@ -139,4 +234,17 @@ models:
     parameters:
       weight: 0.05 # Medical intelligence? Maybe?
       density: 0.05 # Homeopathic dose of medical knowledge
-´´´
+´´´
+# [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-THREADRIPPER-Small-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.55|
+|IFEval (0-Shot)    |76.89|
+|BBH (3-Shot)       |35.79|
+|MATH Lvl 5 (4-Shot)|47.36|
+|GPQA (0-shot)      | 8.05|
+|MuSR (0-shot)      |13.93|
+|MMLU-PRO (5-shot)  |37.30|
+