Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
+base_model: []
+model-index:
+- name: Nemomix-v4.0-12B
+  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: 55.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      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: 32.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      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: 9.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      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: 5.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      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: 12.76
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      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: 29.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MarinaraSpaghetti/Nemomix-v4.0-12B
+      name: Open LLM Leaderboard
 ---
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6550b16f7490049d6237f200/Hj686vH4WgD7ILybOQObi.jpeg)
@@ -99,4 +194,17 @@ dtype: bfloat16
 
 ## Ko-fi
 ### Enjoying what I do? Consider donating here, thank you!
-https://ko-fi.com/spicy_marinara
+https://ko-fi.com/spicy_marinara
+# [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_MarinaraSpaghetti__Nemomix-v4.0-12B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.20|
+|IFEval (0-Shot)    |55.75|
+|BBH (3-Shot)       |32.88|
+|MATH Lvl 5 (4-Shot)| 9.21|
+|GPQA (0-shot)      | 5.59|
+|MuSR (0-shot)      |12.76|
+|MMLU-PRO (5-shot)  |29.03|
+