Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,13 +1,159 @@
 ---
-
-datasets:
-- dominguesm/alpaca-data-pt-br
-library_name: adapter-transformers
-pipeline_tag: text-generation
 language:
 - pt
 - en
+library_name: adapter-transformers
+datasets:
+- dominguesm/alpaca-data-pt-br
+pipeline_tag: text-generation
 thumbnail: https://blog.cobasi.com.br/wp-content/uploads/2022/08/AdobeStock_461738919.webp
+model-index:
+- name: Caramelo_7B
+  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: 19.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 24.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 25.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 54.27
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 7.47
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 43.97
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 33.65
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      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: 41.23
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: tweetSentBR
+      type: eduagarcia-temp/tweetsentbr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 35.37
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Bruno/Caramelo_7B
+      name: Open Portuguese LLM Leaderboard
 ---
 <!-- header start -->
 <div style="width: 100%;">
@@ -126,3 +272,20 @@ Resposta:
 - Pytorch 2.0.1+cu118
 - Datasets 2.12.0
 - Tokenizers 0.13.3
+
+# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Bruno/Caramelo_7B)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**31.73**|
+|ENEM Challenge (No Images)|    19.80|
+|BLUEX (No Images)         |    24.48|
+|OAB Exams                 |    25.28|
+|Assin2 RTE                |    54.27|
+|Assin2 STS                |     7.47|
+|FaQuAD NLI                |    43.97|
+|HateBR Binary             |    33.65|
+|PT Hate Speech Binary     |    41.23|
+|tweetSentBR               |    35.37|
+