Adding Evaluation Results (#1)

- Adding Evaluation Results (1f64eba6f543720ea6a812cc567f607a6eba5050)

README.md

@@ -1,8 +1,17 @@
 ---
-base_model:
-- lunahr/thea-rp-3b-25r
-- HarbingerX/Zeitgeist-3b-V1.2
-- Hastagaras/L3.2-JametMini-3B-MK.III
+language:
+- en
+- de
+- es
+- pt
+- zh
+- fr
+- it
+- ja
+- ko
+- ru
+- mt
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
@@ -19,23 +28,109 @@ tags:
 - lovely
 - i❤️‍🔥jajuka
 - Ad_Æternum
-license: apache-2.0
+base_model:
+- lunahr/thea-rp-3b-25r
+- HarbingerX/Zeitgeist-3b-V1.2
+- Hastagaras/L3.2-JametMini-3B-MK.III
 datasets:
 - Replete-AI/Apocrypha
 - KingNish/reasoning-base-20k
 - lunahr/thea-name-overrides
-language:
-- en
-- de
-- es
-- pt
-- zh
-- fr
-- it
-- ja
-- ko
-- ru
-- mt
+model-index:
+- name: Jajuka-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: 69.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-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: 23.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-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: 15.94
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-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: 2.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-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: 6.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-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: 23.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=RezVortex/Jajuka-3b
+      name: Open LLM Leaderboard
 ---
 # Jajuka 3B AD ÆTERNUM! 🫵❤️‍🩹
 
@@ -179,4 +274,17 @@ merge_method: linear
 dtype: float16
 
 
-```
+```
+# [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/RezVortex__Jajuka-3b-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.48|
+|IFEval (0-Shot)    |69.25|
+|BBH (3-Shot)       |23.20|
+|MATH Lvl 5 (4-Shot)|15.94|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      | 6.59|
+|MMLU-PRO (5-shot)  |23.75|
+