Adding Evaluation Results

README.md

@@ -1,6 +1,101 @@
 ---
 library_name: transformers
 tags: []
+model-index:
+- name: Explore_Llama-3.1-8B-Inst
+  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: 77.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      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: 30.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      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: 17.52
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      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=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      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: 9.64
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      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: 31.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -203,4 +298,17 @@ Model is tested using lm-harness tool version 0.4.3
 
 ## Model Card Contact
 
-For any question contact deepauto.ai
+For any question contact deepauto.ai
+# [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_DeepAutoAI__Explore_Llama-3.1-8B-Inst)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.50|
+|IFEval (0-Shot)    |77.95|
+|BBH (3-Shot)       |30.39|
+|MATH Lvl 5 (4-Shot)|17.52|
+|GPQA (0-shot)      | 4.47|
+|MuSR (0-shot)      | 9.64|
+|MMLU-PRO (5-shot)  |31.02|
+