Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,13 +1,160 @@
 ---
-license: other
-license_name: tongyi-qianwen
-license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
-base_model: Qwen/Qwen2-72B
+license: other
 tags:
 - chat
+base_model: Qwen/Qwen2-72B
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Qwen2-72B-Instruct
+  results:
+  - 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: 82.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 74.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 65.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 94.69
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 75.12
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 84.95
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 84.32
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 74.64
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      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: 76.54
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Qwen/Qwen2-72B-Instruct
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # Qwen2-72B-Instruct
@@ -167,4 +314,23 @@ If you find our work helpful, feel free to give us a cite.
   title={Qwen2 Technical Report},
   year={2024}
 }
-```
+```
+
+
+# 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/Qwen/Qwen2-72B-Instruct) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**79.16**|
+|ENEM Challenge (No Images)|    82.23|
+|BLUEX (No Images)         |    74.41|
+|OAB Exams                 |    65.56|
+|Assin2 RTE                |    94.69|
+|Assin2 STS                |    75.12|
+|FaQuAD NLI                |    84.95|
+|HateBR Binary             |    84.32|
+|PT Hate Speech Binary     |    74.64|
+|tweetSentBR               |    76.54|
+