Adding Evaluation Results (#1)

- Adding Evaluation Results (5a86832d041f2a7156fcb2285145511ac2ffa562)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- meditsolutions/Llama-3.1-MedIT-SUN-8B
-- huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated
-- mlabonne/Hermes-3-Llama-3.1-8B-lorablated
+license: llama3.1
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.1
+base_model:
+- meditsolutions/Llama-3.1-MedIT-SUN-8B
+- huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated
+- mlabonne/Hermes-3-Llama-3.1-8B-lorablated
+model-index:
+- name: Llama_3.1_8b_Hermedive_V1.01
+  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: 50.62
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      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: 27.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      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: 16.47
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      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: 5.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      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: 8.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      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: 28.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.1_8b_Hermedive_V1.01
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -43,4 +138,17 @@ normalize: true
 chat_template: auto
 tokenizer:
   source: union
-```
+```
+# [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/Nexesenex__Llama_3.1_8b_Hermedive_V1.01-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.79|
+|IFEval (0-Shot)    |50.62|
+|BBH (3-Shot)       |27.65|
+|MATH Lvl 5 (4-Shot)|16.47|
+|GPQA (0-shot)      | 5.26|
+|MuSR (0-shot)      | 8.41|
+|MMLU-PRO (5-shot)  |28.34|
+