Adding Evaluation Results (#1)

- Adding Evaluation Results (4622e9d91bda471e794aa8225c26ed17fadc5e77)

README.md

@@ -8,6 +8,105 @@ tags:
 - mergekit
 - merge
 license: llama3.2
+model-index:
+- name: Llama_3.2_3b_Kermes_v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 57.54
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 22.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 5.44
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      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: 4.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      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: 19.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Nexesenex%2FLlama_3.2_3b_Kermes_v2
+      name: Open LLM Leaderboard
 ---
 
 ---
@@ -53,4 +152,18 @@ models:
 base_model: Nexesenex/Llama_3.2_3b_Kermes_0.2_bf16
 dtype: float16
 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/Nexesenex__Llama_3.2_3b_Kermes_v2-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Nexesenex%2FLlama_3.2_3b_Kermes_v2&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    18.50|
+|IFEval (0-Shot)    |    57.54|
+|BBH (3-Shot)       |    22.05|
+|MATH Lvl 5 (4-Shot)|     5.44|
+|GPQA (0-shot)      |     2.01|
+|MuSR (0-shot)      |     4.66|
+|MMLU-PRO (5-shot)  |    19.27|
+