Adding Evaluation Results (#1)

- Adding Evaluation Results (3e28b50730d0648bffa26b5dc1e24eeda993c917)

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- DavidAU/L3.1-RP-Hero-Dirty_Harry-8B
-- NousResearch/Hermes-3-Llama-3.1-8B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- DavidAU/L3.1-RP-Hero-Dirty_Harry-8B
+- NousResearch/Hermes-3-Llama-3.1-8B
+model-index:
+- name: Hermes3-L3.1-DirtyHarry-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: 32.42
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-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: 29.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-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: 7.18
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-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: 6.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-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: 9.16
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-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: 25.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes3-L3.1-DirtyHarry-8B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,3 +138,17 @@ parameters:
   int8_mask: true
 dtype: float16
 ```
+
+# [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/Triangle104__Hermes3-L3.1-DirtyHarry-8B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.56|
+|IFEval (0-Shot)    |32.42|
+|BBH (3-Shot)       |29.68|
+|MATH Lvl 5 (4-Shot)| 7.18|
+|GPQA (0-shot)      | 6.94|
+|MuSR (0-shot)      | 9.16|
+|MMLU-PRO (5-shot)  |25.98|
+