Adding Evaluation Results

README.md

@@ -20,8 +20,7 @@ model-index:
       value: 73.81
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -37,8 +36,7 @@ model-index:
       value: 89.22
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -55,8 +53,7 @@ model-index:
       value: 64.92
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -72,8 +69,7 @@ model-index:
     - type: mc2
       value: 78.57
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -90,8 +86,7 @@ model-index:
       value: 87.37
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -108,8 +103,99 @@ model-index:
       value: 71.11
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      name: Open LLM Leaderboard
+  - 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: 41.88
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      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: 19.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      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: 5.97
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      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: 6.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      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: 8.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
+      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: 20.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
       name: Open LLM Leaderboard
 ---
 
@@ -143,4 +229,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MMLU (5-Shot)                    |64.92|
 |TruthfulQA (0-shot)              |78.57|
 |Winogrande (5-shot)              |87.37|
-|GSM8k (5-shot)                   |71.11|
+|GSM8k (5-shot)                   |71.11|
+# [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_zhengr__MixTAO-7Bx2-MoE-v8.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.06|
+|IFEval (0-Shot)    |41.88|
+|BBH (3-Shot)       |19.18|
+|MATH Lvl 5 (4-Shot)| 5.97|
+|GPQA (0-shot)      | 6.49|
+|MuSR (0-shot)      | 8.30|
+|MMLU-PRO (5-shot)  |20.52|
+