Adding Evaluation Results (#1)

- Adding Evaluation Results (533c8e78c9a31f112314cf1c55c1ad14aad2bc27)

README.md

@@ -1,4 +1,8 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - passing2961/Thanos-3B
 - prithivMLmods/Llama-Sentient-3.2-3B-Instruct
@@ -7,11 +11,101 @@ base_model:
 - huihui-ai/Llama-3.2-3B-Instruct-abliterated
 - prithivMLmods/Codepy-Deepthink-3B
 - HuggingFaceTB/finemath-ablation-infiwebmath
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Smol-Llama-3.2-3B
+  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: 66.79
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      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: 23.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      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: 13.52
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      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: 3.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      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: 3.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      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: 24.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Smol-Llama-3.2-3B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -74,3 +168,17 @@ models:
       density: 0.8
 
 ```
+
+# [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/bunnycore__Smol-Llama-3.2-3B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.47|
+|IFEval (0-Shot)    |66.79|
+|BBH (3-Shot)       |23.04|
+|MATH Lvl 5 (4-Shot)|13.52|
+|GPQA (0-shot)      | 3.58|
+|MuSR (0-shot)      | 3.15|
+|MMLU-PRO (5-shot)  |24.76|
+