Adding Evaluation Results

README.md

@@ -6,6 +6,101 @@ library_name: transformers
 tags:
 - mergekit
 - merge
+model-index:
+- name: Meta-Llama-3.1-8B-Instruct-TIES
+  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: 54.24
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      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: 29.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      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: 20.02
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      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: 5.93
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      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: 8.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      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: 30.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Meta-Llama-3.1-8B-Instruct-TIES
+      name: Open LLM Leaderboard
 ---
 # Rombo Llama Merge Test
 
@@ -46,3 +141,18 @@ slices:
     model: unsloth/Meta-Llama-3.1-8B
 tokenizer_source: unsloth/Meta-Llama-3.1-8B-Instruct
 ```
+
+# [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/T145__Meta-Llama-3.1-8B-Instruct-TIES-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145/Meta-Llama-3.1-8B-Instruct-TIES)!
+
+|      Metric       |% Value|
+|-------------------|------:|
+|Avg.               |  24.81|
+|IFEval (0-Shot)    |  54.24|
+|BBH (3-Shot)       |  29.77|
+|MATH Lvl 5 (4-Shot)|  20.02|
+|GPQA (0-shot)      |   5.93|
+|MuSR (0-shot)      |   8.04|
+|MMLU-PRO (5-shot)  |  30.89|
+