Adding Evaluation Results (#1)

- Adding Evaluation Results (be106ae651004ee8e22cdea69571714f22a4b077)

README.md

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - elinas/Chronos-Gold-12B-1.0
 - nbeerbower/mistral-nemo-gutenberg3-12B
@@ -6,11 +11,101 @@ base_model:
 - nothingiisreal/MN-12B-Celeste-V1.9
 - Gryphe/Pantheon-RP-1.6.1-12b-Nemo
 - anthracite-org/magnum-v4-12b
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: Annunaki-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: 38.72
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-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: 35.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-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: 11.33
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-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: 9.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-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: 14.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-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: 30.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Annunaki-12b
+      name: Open LLM Leaderboard
 ---
 # Merge
 
@@ -55,4 +150,17 @@ parameters:
   normalize: true
 dtype: bfloat16
 
-```
+```
+# [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/Triangle104__Annunaki-12b-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.23|
+|IFEval (0-Shot)    |38.72|
+|BBH (3-Shot)       |35.32|
+|MATH Lvl 5 (4-Shot)|11.33|
+|GPQA (0-shot)      | 9.51|
+|MuSR (0-shot)      |14.28|
+|MMLU-PRO (5-shot)  |30.23|
+