Adding Evaluation Results (#1)

- Adding Evaluation Results (b1ff04d3cb4237971dd5f8c9b9e743a56674eb00)


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

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 language:
 - de
 - en
@@ -9,15 +8,111 @@ language:
 - nl
 - ar
 - es
+license: apache-2.0
 tags:
 - spectrum
 - sft
 - dpo
+base_model:
+- VAGOsolutions/SauerkrautLM-v2-14b-SFT
 datasets:
 - VAGOsolutions/SauerkrautLM-Fermented-GER-DPO
 - VAGOsolutions/SauerkrautLM-Fermented-Irrelevance-GER-DPO
-base_model:
-- VAGOsolutions/SauerkrautLM-v2-14b-SFT
+model-index:
+- name: SauerkrautLM-v2-14b-DPO
+  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: 74.12
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      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: 50.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      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: 27.34
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      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: 9.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      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: 13.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      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: 45.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-DPO
+      name: Open LLM Leaderboard
 ---
 
 
@@ -137,4 +232,17 @@ If you are interested in customized LLMs for business applications, please get i
 We are also keenly seeking support and investment for our startup, VAGO solutions where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at [VAGO solutions](https://vago-solutions.ai)
 
 ## Acknowledgement
-Many thanks to [Qwen](https://huggingface.co/Qwen) for providing such a valuable base model, and to our community for their continued support and engagement.
+Many thanks to [Qwen](https://huggingface.co/Qwen) for providing such a valuable base model, and to our community for their continued support and engagement.
+# [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_VAGOsolutions__SauerkrautLM-v2-14b-DPO)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.87|
+|IFEval (0-Shot)    |74.12|
+|BBH (3-Shot)       |50.93|
+|MATH Lvl 5 (4-Shot)|27.34|
+|GPQA (0-shot)      | 9.28|
+|MuSR (0-shot)      |13.78|
+|MMLU-PRO (5-shot)  |45.75|
+