Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,31 +1,31 @@
 ---
-license: apache-2.0
-datasets:
-- nicholasKluge/instruct-aira-dataset-v2
 language:
 - pt
-metrics:
-- accuracy
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
 tags:
 - alignment
 - instruction tuned
 - text generation
 - conversation
 - assistant
+datasets:
+- nicholasKluge/instruct-aira-dataset-v2
+metrics:
+- accuracy
+pipeline_tag: text-generation
 widget:
-- text: "<s><instruction>Cite algumas bandas de rock famosas da década de 1960.</instruction>"
+- text: <s><instruction>Cite algumas bandas de rock famosas da década de 1960.</instruction>
   example_title: Exemplo
-- text: "<s><instruction>Quantos planetas existem no sistema solar?</instruction>"
+- text: <s><instruction>Quantos planetas existem no sistema solar?</instruction>
   example_title: Exemplo
-- text: "<s><instruction>Qual é o futuro do ser humano?</instruction>"
+- text: <s><instruction>Qual é o futuro do ser humano?</instruction>
   example_title: Exemplo
-- text: "<s><instruction>Qual o sentido da vida?</instruction>"
+- text: <s><instruction>Qual o sentido da vida?</instruction>
   example_title: Exemplo
-- text: "<s><instruction>Como imprimir hello world em python?</instruction>"
+- text: <s><instruction>Como imprimir hello world em python?</instruction>
   example_title: Exemplo
-- text: "<s><instruction>Invente uma história sobre um encanador com poderes mágicos.</instruction>"
+- text: <s><instruction>Invente uma história sobre um encanador com poderes mágicos.</instruction>
   example_title: Exemplo
 inference:
   parameters:
@@ -42,6 +42,153 @@ co2_eq_emissions:
   training_type: fine-tuning
   geographical_location: United States of America
   hardware_used: NVIDIA A100-SXM4-40GB
+model-index:
+- name: TeenyTinyLlama-460m-Chat
+  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: 20.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 25.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 26.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 43.77
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 4.52
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 34.0
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 33.49
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 22.99
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      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: 18.13
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-460m-Chat
+      name: Open Portuguese LLM Leaderboard
 ---
 # TeenyTinyLlama-460m-Chat
 
@@ -233,4 +380,20 @@ This repository was built as part of the RAIES ([Rede de Inteligência Artificia
 
 ## License
 
-TeenyTinyLlama-460m-Chat is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
+TeenyTinyLlama-460m-Chat is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
+# [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/nicholasKluge/TeenyTinyLlama-460m-Chat)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**25.49**|
+|ENEM Challenge (No Images)|    20.29|
+|BLUEX (No Images)         |    25.45|
+|OAB Exams                 |    26.74|
+|Assin2 RTE                |    43.77|
+|Assin2 STS                |     4.52|
+|FaQuAD NLI                |       34|
+|HateBR Binary             |    33.49|
+|PT Hate Speech Binary     |    22.99|
+|tweetSentBR               |    18.13|
+