Adding Evaluation Results

README.md

@@ -110,6 +110,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
       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: 42.84
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 45.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 20.62
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 16.22
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 14.76
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 41.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      name: Open LLM Leaderboard
 ---
 
 #
@@ -225,3 +317,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 
 5th in 34B size range excluding "Private or deleted" or 8th with all models included as of 2024-06-10 ;P
 <img src=https://huggingface.co/altomek/YiSM-34B-0rn/resolve/main/5thIn34B.png>
+
+# [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_altomek__YiSM-34B-0rn)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.15|
+|IFEval (0-Shot)    |42.84|
+|BBH (3-Shot)       |45.38|
+|MATH Lvl 5 (4-Shot)|20.62|
+|GPQA (0-shot)      |16.22|
+|MuSR (0-shot)      |14.76|
+|MMLU-PRO (5-shot)  |41.06|
+