Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
-datasets:
-- BAAI/Infinity-Instruct
 language:
 - en
 base_model: google/gemma-2-2b-it
+datasets:
+- BAAI/Infinity-Instruct
+model-index:
+- name: Gemma2-9B-IT-Simpo-Infinity-Preference
+  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: 31.76
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      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: 42.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      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: 11.97
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      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: 8.1
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      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: 31.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
+      name: Open LLM Leaderboard
 ---
 
 ## Overview
@@ -83,3 +178,17 @@ print(response)
 ## Disclaimer
 
 The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of Infinity-Preference is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.
+
+# [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_BAAI__Gemma2-9B-IT-Simpo-Infinity-Preference)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.97|
+|IFEval (0-Shot)    |31.76|
+|BBH (3-Shot)       |42.19|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      |11.97|
+|MuSR (0-shot)      | 8.10|
+|MMLU-PRO (5-shot)  |31.82|
+