Adding Evaluation Results (#1)

- Adding Evaluation Results (f3d94dd6a9a319874edece70033dc0f7f586908f)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
-- nbeerbower/Llama3.1-Allades-8B
-- DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
+license: llama3.1
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.1
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+- nbeerbower/Llama3.1-Allades-8B
+- DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
+model-index:
+- name: Distilled-DarkPlanet-Allades-8B
+  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: 34.6
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B
+      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=Triangle104/Distilled-DarkPlanet-Allades-8B
+      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: 33.84
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B
+      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: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B
+      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: 3.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B
+      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: 21.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -45,4 +140,17 @@ parameters:
   int8_mask: true
 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/Triangle104__Distilled-DarkPlanet-Allades-8B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.65|
+|IFEval (0-Shot)    |34.60|
+|BBH (3-Shot)       |23.04|
+|MATH Lvl 5 (4-Shot)|33.84|
+|GPQA (0-shot)      | 7.38|
+|MuSR (0-shot)      | 3.92|
+|MMLU-PRO (5-shot)  |21.13|
+