Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -17,8 +17,7 @@ model-index:
       value: 76.49
       name: strict accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -33,8 +32,7 @@ model-index:
       value: 42.25
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -49,8 +47,7 @@ model-index:
       value: 1.74
       name: exact match
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -65,8 +62,7 @@ model-index:
       value: 10.74
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -81,8 +77,7 @@ model-index:
       value: 12.39
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -99,9 +94,152 @@ model-index:
       value: 35.63
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
       name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ENEM Challenge (No Images)
+      type: eduagarcia/enem_challenge
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 75.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BLUEX (No Images)
+      type: eduagarcia-temp/BLUEX_without_images
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 64.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: OAB Exams
+      type: eduagarcia/oab_exams
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 53.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 RTE
+      type: assin2
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 93.21
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 STS
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: pearson
+      value: 80.91
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: FaQuAD NLI
+      type: ruanchaves/faquad-nli
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 77.39
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HateBR Binary
+      type: ruanchaves/hatebr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 87.61
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: PT Hate Speech Binary
+      type: hate_speech_portuguese
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 66.84
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: tweetSentBR
+      type: eduagarcia/tweetsentbr_fewshot
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 66.14
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # Gemma-2-Ataraxy-Gemmasutra-9B-slerp
@@ -142,4 +280,23 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)| 1.74|
 |GPQA (0-shot)      |10.74|
 |MuSR (0-shot)      |12.39|
-|MMLU-PRO (5-shot)  |35.63|
+|MMLU-PRO (5-shot)  |35.63|
+
+
+# Open Portuguese LLM Leaderboard Evaluation Results  
+
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**73.97**|
+|ENEM Challenge (No Images)|    75.65|
+|BLUEX (No Images)         |    64.26|
+|OAB Exams                 |    53.76|
+|Assin2 RTE                |    93.21|
+|Assin2 STS                |    80.91|
+|FaQuAD NLI                |    77.39|
+|HateBR Binary             |    87.61|
+|PT Hate Speech Binary     |    66.84|
+|tweetSentBR               |    66.14|
+