Adding Evaluation Results

README.md

@@ -1,18 +1,113 @@
 ---
-base_model:
-- sthenno-com/miscii-14b-1225
-- sometimesanotion/Qwen2.5-14B-Vimarckoso-v3
+language:
+- en
+- zh
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
-language:
-- en
-- zh
+base_model:
+- sthenno-com/miscii-14b-1225
+- sometimesanotion/Qwen2.5-14B-Vimarckoso-v3
 metrics:
 - accuracy
 new_version: sthenno/tempesthenno-14b-nuslerp-0111
+model-index:
+- name: tempesthenno-nuslerp-001
+  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: 79.26
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      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: 51.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      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: 31.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      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: 16.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      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: 13.88
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      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: 47.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno/tempesthenno-nuslerp-001
+      name: Open LLM Leaderboard
 ---
 # tempesthenno--nuslerp
 
@@ -121,4 +216,17 @@ 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-001-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.94|
+|IFEval (0-Shot)    |79.26|
+|BBH (3-Shot)       |51.04|
+|MATH Lvl 5 (4-Shot)|31.72|
+|GPQA (0-shot)      |16.44|
+|MuSR (0-shot)      |13.88|
+|MMLU-PRO (5-shot)  |47.30|
+