Adding Evaluation Results (#1)

- Adding Evaluation Results (75abf2612b6b92a2a1b52ae15bbbcddd9271fb46)

README.md

@@ -1,11 +1,12 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
 - lazymergekit
-language:
-- en
 base_model:
 - bunnycore/Llama-3.1-8B-TitanFusion-Test
 - vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
@@ -13,7 +14,101 @@ base_model:
 - bunnycore/Llama-3.1-8B-TitanFusion-Mix
 - kromeurus/L3.1-Siithamo-v0.4-8B
 pipeline_tag: text-generation
-library_name: transformers
+model-index:
+- name: Llama-3.1-8B-SpecialTitanFusion
+  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: 74.02
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      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: 34.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      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: 23.34
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      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: 6.6
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      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: 7.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      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: 29.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Llama-3.1-8B-SpecialTitanFusion
+      name: Open LLM Leaderboard
 ---
 
 # 🏆 ZeroXClem-Llama-3.1-8B-SpecialTitanFusion 🏆  
@@ -142,4 +237,17 @@ This model follows **Meta’s Llama-3.1 Community License Agreement**. It is an
 Please ensure compliance with ethical AI guidelines when deploying this model in production environments.  
 
 ## 💬 Feedback & Contributions  
-If you have suggestions or improvements, feel free to **open a discussion on Hugging Face**! Let's continue improving the **Llama-3.1 merging meta-game!** 🚀
+If you have suggestions or improvements, feel free to **open a discussion on Hugging Face**! Let's continue improving the **Llama-3.1 merging meta-game!** 🚀
+# [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/ZeroXClem__Llama-3.1-8B-SpecialTitanFusion-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.23|
+|IFEval (0-Shot)    |74.02|
+|BBH (3-Shot)       |34.82|
+|MATH Lvl 5 (4-Shot)|23.34|
+|GPQA (0-shot)      | 6.60|
+|MuSR (0-shot)      | 7.49|
+|MMLU-PRO (5-shot)  |29.12|
+