Adding Evaluation Results (#2)

- Adding Evaluation Results (21c294477b1e5f5c528cd3b6f3149885fae673a3)


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

README.md

@@ -156,6 +156,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
       name: Open Portuguese 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: 28.92
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      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: 5.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      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: 0.38
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      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: 10.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      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: 5.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OliveiraJLT/Sagui-7B-Instruct-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Sagui-7B-Instruct-v0.1
@@ -271,3 +363,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-
 |PT Hate Speech Binary     |    30.38|
 |tweetSentBR               |    18.34|
 
+
+# [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_OliveiraJLT__Sagui-7B-Instruct-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 8.39|
+|IFEval (0-Shot)    |28.92|
+|BBH (3-Shot)       | 5.04|
+|MATH Lvl 5 (4-Shot)| 0.38|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      |10.61|
+|MMLU-PRO (5-shot)  | 5.39|
+