Update README.md

README.md

@@ -1,20 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - allknowingroger/Qwenslerp2-14B
 - rombodawg/Rombos-LLM-V2.6-Qwen-14b
 - VAGOsolutions/SauerkrautLM-v2-14b-DPO
 - Qwen/Qwen2.5-14B
 - CultriX/Qwen2.5-14B-Wernicke
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
-language:
-- en
-metrics:
-- accuracy
-pipeline_tag: text-generation
+model-index:
+- name: Qwestion-14B
+  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: 63.18
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
+      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: 48.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
+      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=CultriX/Qwestion-14B
+      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: 15.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
+      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: 17.22
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
+      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: 49.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwestion-14B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -72,4 +161,17 @@ adaptive_merge_parameters:
   smoothing_factor: 0.15   # Fine-tune blending for stable transitions between tasks
 gradient_clipping: 1.0      # Prevent over-contribution from any single model
 
-```
+```
+
+# [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/details_CultriX__Qwestion-14B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |37.63|
+|IFEval (0-Shot)    |63.18|
+|BBH (3-Shot)       |48.76|
+|MATH Lvl 5 (4-Shot)|31.72|
+|GPQA (0-shot)      |15.77|
+|MuSR (0-shot)      |17.22|
+|MMLU-PRO (5-shot)  |49.14|