Adding Evaluation Results (#1)

- Adding Evaluation Results (cb6c33554644cd67f2ea2509459fac908a8c9c06)

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- bunnycore/Llama-3.2-3B-KodCode-R1
-- bunnycore/Llama-3.2-3b-RP-Toxic-R1
-- unsloth/Llama-3.2-3B-Instruct
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- bunnycore/Llama-3.2-3B-KodCode-R1
+- bunnycore/Llama-3.2-3b-RP-Toxic-R1
+- unsloth/Llama-3.2-3B-Instruct
+model-index:
+- name: Llama-3.2-3B-ToxicKod
+  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: 63.19
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      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: 22.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      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: 16.99
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      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: 2.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      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: 1.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      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: 20.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-ToxicKod
+      name: Open LLM Leaderboard
 ---
 
 This model is intended to be uncensored, and it can also role-play and use reasoning.
@@ -46,3 +140,17 @@ parameters:
 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/bunnycore__Llama-3.2-3B-ToxicKod-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.27|
+|IFEval (0-Shot)    |63.19|
+|BBH (3-Shot)       |22.98|
+|MATH Lvl 5 (4-Shot)|16.99|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      | 1.43|
+|MMLU-PRO (5-shot)  |20.89|
+