Adding Evaluation Results

README.md

@@ -1,5 +1,100 @@
 ---
 license: llama3
+model-index:
+- name: Llama-3.1-8B-ArliAI-RPMax-v1.1
+  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: 63.59
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      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: 28.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      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: 11.33
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      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: 4.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      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: 5.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      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: 28.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3.1-8B-ArliAI-RPMax-v1.1
@@ -63,4 +158,17 @@ You are [character]. You have a personality of [personality description]. [Descr
 {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
 
 {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-```
+```
+# [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_ArliAI__Llama-3.1-8B-ArliAI-RPMax-v1.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.64|
+|IFEval (0-Shot)    |63.59|
+|BBH (3-Shot)       |28.79|
+|MATH Lvl 5 (4-Shot)|11.33|
+|GPQA (0-shot)      | 4.47|
+|MuSR (0-shot)      | 5.31|
+|MMLU-PRO (5-shot)  |28.35|
+