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

@@ -1,20 +1,115 @@
 ---
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
-- sthenno-com/miscii-14b-1225
-- sthenno/tempesthenno-ppo-ckpt40
-- sometimesanotion/Qwenvergence-14B-v10
+language:
+- en
+- zh
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
 - custom-research
-license: apache-2.0
-language:
-- en
-- zh
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
+- sthenno-com/miscii-14b-1225
+- sthenno/tempesthenno-ppo-ckpt40
+- sometimesanotion/Qwenvergence-14B-v10
 metrics:
 - accuracy
+model-index:
+- name: tempesthenno-nuslerp-0124
+  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: 70.04
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      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: 49.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      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: 39.27
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      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: 18.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      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: 20.21
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      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: 48.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-0124
+      name: Open LLM Leaderboard
 ---
 
 update: now checking the evaluations without chat templates
@@ -126,4 +221,17 @@ slices:
           weight: 0.60
           nuslerp_flatten: true
 
-```
+```
+# [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/sthenno__tempesthenno-nuslerp-0124-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |40.97|
+|IFEval (0-Shot)    |70.04|
+|BBH (3-Shot)       |49.28|
+|MATH Lvl 5 (4-Shot)|39.27|
+|GPQA (0-shot)      |18.68|
+|MuSR (0-shot)      |20.21|
+|MMLU-PRO (5-shot)  |48.36|
+