Adding Evaluation Results (#1)

- Adding Evaluation Results (528432f15da547ab2e3e714a48923ff8386690a9)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,12 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+- roleplay
+- llama
+- llama-3.1
 base_model:
 - NeverSleep/Lumimaid-v0.2-8B
 - kloodia/lora-8b-medic
@@ -9,14 +17,101 @@ base_model:
 - vicgalle/Configurable-Llama-3.1-8B-Instruct
 - kloodia/lora-8b-physic
 - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
-library_name: transformers
-tags:
-- mergekit
-- merge
-- roleplay
-- llama
-- llama-3.1
-license: apache-2.0
+model-index:
+- name: Gluon-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: 50.53
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-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: 30.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-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: 12.54
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-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: 8.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-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: 9.09
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-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: 31.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rmdhirr/Gluon-8B
+      name: Open LLM Leaderboard
 ---
 # ⚛️ Gluon-8B
 
@@ -51,4 +146,17 @@ base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
 normalize: true
 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/details_rmdhirr__Gluon-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.66|
+|IFEval (0-Shot)    |50.53|
+|BBH (3-Shot)       |30.34|
+|MATH Lvl 5 (4-Shot)|12.54|
+|GPQA (0-shot)      | 8.28|
+|MuSR (0-shot)      | 9.09|
+|MMLU-PRO (5-shot)  |31.20|
+