Adding Evaluation Results

README.md

@@ -107,6 +107,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
       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: 52.49
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      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: 46.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      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: 16.16
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      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: 13.87
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      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: 18.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      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: 42.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MTSAIR/MultiVerse_70B
+      name: Open LLM Leaderboard
 ---
 ## This model is based on Qwen 72B
 **Note:** 
@@ -126,3 +218,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |Winogrande (5-shot)              |87.53|
 |GSM8k (5-shot)                   |76.65|
 
+
+# [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_MTSAIR__MultiVerse_70B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.73|
+|IFEval (0-Shot)    |52.49|
+|BBH (3-Shot)       |46.14|
+|MATH Lvl 5 (4-Shot)|16.16|
+|GPQA (0-shot)      |13.87|
+|MuSR (0-shot)      |18.82|
+|MMLU-PRO (5-shot)  |42.89|
+