Adding Evaluation Results

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- cognitivecomputations/dolphin-2.2.1-mistral-7b
-- teknium/OpenHermes-2.5-Mistral-7B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- cognitivecomputations/dolphin-2.2.1-mistral-7b
+- teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: RuDolph-Hermes-7B
+  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: 36.04
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      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: 30.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      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: 5.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      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: 8.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      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: 11.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      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: 23.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/RuDolph-Hermes-7B
+      name: Open LLM Leaderboard
 ---
 <img src="https://huggingface.co/theprint/RuDolph-Hermes-7B/resolve/main/rudolph_finn_hermes.png">
 
@@ -50,3 +144,17 @@ dtype: bfloat16
 parameters:
   t: [0.2, 0.3, 0.5, 0.7, 0.8]
 ```
+
+# [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_theprint__RuDolph-Hermes-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.02|
+|IFEval (0-Shot)    |36.04|
+|BBH (3-Shot)       |30.71|
+|MATH Lvl 5 (4-Shot)| 5.06|
+|GPQA (0-shot)      | 8.28|
+|MuSR (0-shot)      |11.03|
+|MMLU-PRO (5-shot)  |23.03|
+