Adding Evaluation Results (#3)

- Adding Evaluation Results (63c2617a82354ab3d4041f8f20957e1ae5959412)


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

README.md

@@ -1,11 +1,106 @@
 ---
+license: apache-2.0
 library_name: transformers
 tags:
 - safety
-license: apache-2.0
 base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
 datasets:
 - vicgalle/configurable-system-prompt-multitask
+model-index:
+- name: Configurable-Hermes-2-Pro-Llama-3-8B
+  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: 57.63
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      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: 30.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      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: 5.97
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      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: 6.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      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: 10.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      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: 23.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
+      name: Open LLM Leaderboard
 ---
 
 # Configurable-LLama-3-8B
@@ -94,3 +189,17 @@ If you find this work, data and/or models useful for your research, please consi
       primaryClass={cs.CL}
 }
 ```
+
+# [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_vicgalle__Configurable-Hermes-2-Pro-Llama-3-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.29|
+|IFEval (0-Shot)    |57.63|
+|BBH (3-Shot)       |30.51|
+|MATH Lvl 5 (4-Shot)| 5.97|
+|GPQA (0-shot)      | 6.26|
+|MuSR (0-shot)      |10.06|
+|MMLU-PRO (5-shot)  |23.31|
+