Adding Evaluation Results (#5)

- Adding Evaluation Results (080036b5a65c18047d6c4d7b7c2985e02ef8140b)


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

README.md

@@ -1,9 +1,104 @@
 ---
+license: apache-2.0
 tags:
 - yi
 - moe
 - DPO
-license: apache-2.0
+model-index:
+- name: Yi-34Bx2-MoE-60B-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: 53.19
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-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: 31.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-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: 6.19
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-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: 9.62
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-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: 14.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-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: 40.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO
+      name: Open LLM Leaderboard
 ---
 
 
@@ -12,4 +107,17 @@ license: apache-2.0
 
  * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer)
 
- * metrics not test!
+ * metrics not test!
+# [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_cloudyu__Yi-34Bx2-MoE-60B-DPO)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.91|
+|IFEval (0-Shot)    |53.19|
+|BBH (3-Shot)       |31.26|
+|MATH Lvl 5 (4-Shot)| 6.19|
+|GPQA (0-shot)      | 9.62|
+|MuSR (0-shot)      |14.32|
+|MMLU-PRO (5-shot)  |40.85|
+