Update README.md

README.md

@@ -17,6 +17,101 @@ base_model:
 pipeline_tag: text-generation
 tags:
 - merge
+model-index:
+- name: ZYH-LLM-Qwen2.5-14B-V4
+  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: 83.65
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      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: 50.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      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: 53.93
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      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: 8.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      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: 15.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      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: 46.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
+      name: Open LLM Leaderboard
 ---
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e174e202fa032de4143324/CpkVlkXWV0_9Qnz0nDIP4.jpeg)
 # ZYH-LLM-Qwen2.5-14B-V4
@@ -43,6 +138,21 @@ Using the above template for merging can improve the **calculation accuracy** an
 
 **ZYH-LLM-Qwen2.5-V4** used this template during the model merging process.
 
+# [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/YOYO-AI__ZYH-LLM-Qwen2.5-14B-V3-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |43.14|
+|IFEval (0-Shot)    |83.65|
+|BBH (3-Shot)       |50.27|
+|MATH Lvl 5 (4-Shot)|53.93|
+|GPQA (0-shot)      |8.61|
+|MuSR (0-shot)      |15.66|
+|MMLU-PRO (5-shot)  |46.71|
+
+The following are the specific details of model merging, hoping to inspire you:
+
 ## First stage:
 *Create four different instruction models and code model*
 ```yaml