Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
+language:
+- en
+license: llama3.1
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - SicariusSicariiStuff/Dusk_Rainbow
 - unsloth/DeepSeek-R1-Distill-Llama-8B
 - allura-org/L3.1-8b-RP-Ink
 - unsloth/Meta-Llama-3.1-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: llama3.1
-language:
-- en
+model-index:
+- name: L3.1-8B-Dusky-Ink_v0.r1
+  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: 19.85
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      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: 20.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      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: 4.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      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: 7.16
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      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: 7.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      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: 24.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/L3.1-8B-Dusky-Ink_v0.r1
+      name: Open LLM Leaderboard
 ---
 # Merge
 
@@ -44,4 +139,17 @@ parameters:
     normalize: 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__L3.1-8B-Dusky-Ink_v0.r1-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.97|
+|IFEval (0-Shot)    |19.85|
+|BBH (3-Shot)       |20.18|
+|MATH Lvl 5 (4-Shot)| 4.31|
+|GPQA (0-shot)      | 7.16|
+|MuSR (0-shot)      | 7.82|
+|MMLU-PRO (5-shot)  |24.51|
+