Adding Evaluation Results (#1)

- Adding Evaluation Results (1b44a3e362e6af3d94a4b364320cde0ed5868aa8)

README.md

@@ -1,17 +1,112 @@
 ---
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
-- Qwen/Qwen2.5-7B
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
 - qwen2.5
 - TIES
-language:
-- en
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+- Qwen/Qwen2.5-7B
 pipeline_tag: text-generation
+model-index:
+- name: Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+  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: 75.64
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      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: 34.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      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=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      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: 6.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      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: 8.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      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: 37.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CombinHorizon/Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -66,4 +161,17 @@ The merge is based on the technique posted [here](https://huggingface.co/romboda
       author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
       journal={arXiv preprint arXiv:2407.10671},
       year={2024}
-}
+}
+# [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_CombinHorizon__Rombos-Qwen2.5-7B-Inst-BaseMerge-TIES)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.15|
+|IFEval (0-Shot)    |75.64|
+|BBH (3-Shot)       |34.95|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 6.38|
+|MuSR (0-shot)      | 8.78|
+|MMLU-PRO (5-shot)  |37.13|
+