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

@@ -1,4 +1,12 @@
 ---
+language:
+- en
+- zh
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - sthenno/tempesthenno-0126-ckpt150
 - ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign
@@ -7,14 +15,101 @@ base_model:
 - sthenno-com/miscii-14b-1225
 - sthenno/tempesthenno-nuslerp-0124
 - huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
-library_name: transformers
-tags:
-- mergekit
-- merge
-language:
-- en
-- zh
-license: apache-2.0
+model-index:
+- name: miscii-14b-1M-0128
+  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: 41.81
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      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: 37.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      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: 40.18
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      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: 17.67
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      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: 28.75
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      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: 38.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
+      name: Open LLM Leaderboard
 ---
 
 # merge
@@ -59,4 +154,17 @@ parameters:
 dtype: bfloat16
 normalize: 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/win10__miscii-14b-1M-0128-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.08|
+|IFEval (0-Shot)    |41.81|
+|BBH (3-Shot)       |37.27|
+|MATH Lvl 5 (4-Shot)|40.18|
+|GPQA (0-shot)      |17.67|
+|MuSR (0-shot)      |28.75|
+|MMLU-PRO (5-shot)  |38.79|
+