Adding Evaluation Results

README.md

@@ -1,10 +1,105 @@
 ---
-license: other
 language:
 - zh
 - en
+license: other
 datasets:
 - thomas-yanxin/MT-SFT-ShareGPT
+model-index:
+- name: XinYuan-Qwen2-7B
+  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: 44.32
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      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: 28.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      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: 12.01
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      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: 5.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      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: 9.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      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: 32.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=thomas-yanxin/XinYuan-Qwen2-7B
+      name: Open LLM Leaderboard
 ---
 
 
@@ -27,4 +122,17 @@ Here are the results from our OpenCompass evaluation：
 | Chinese       | C-EVAL  | 82.0             |
 |            | CMMLU   | 77.9             |
 | Code       | MBPP    | 50.6             |
-|            | HumanEval | 70.1             |
+|            | HumanEval | 70.1             |
+# [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_thomas-yanxin__XinYuan-Qwen2-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.99|
+|IFEval (0-Shot)    |44.32|
+|BBH (3-Shot)       |28.40|
+|MATH Lvl 5 (4-Shot)|12.01|
+|GPQA (0-shot)      | 5.48|
+|MuSR (0-shot)      | 9.26|
+|MMLU-PRO (5-shot)  |32.49|
+