Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,21 +1,21 @@
 ---
+language:
+- pt
 license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
 datasets:
 - nicholasKluge/Pt-Corpus-Instruct
-language:
-- pt
 metrics:
 - perplexity
-library_name: transformers
 pipeline_tag: text-generation
-tags:
-- text-generation-inference
 widget:
-- text: "A PUCRS é uma universidade "
+- text: 'A PUCRS é uma universidade '
   example_title: Exemplo
-- text: "A muitos anos atrás, em uma galáxia muito distante, vivia uma raça de"
+- text: A muitos anos atrás, em uma galáxia muito distante, vivia uma raça de
   example_title: Exemplo
-- text: "Em meio a um escândalo, a frente parlamentar pediu ao Senador Silva para"
+- text: Em meio a um escândalo, a frente parlamentar pediu ao Senador Silva para
   example_title: Exemplo
 inference:
   parameters:
@@ -30,6 +30,153 @@ co2_eq_emissions:
   training_type: pre-training
   geographical_location: Germany
   hardware_used: NVIDIA A100-SXM4-40GB
+model-index:
+- name: TeenyTinyLlama-160m
+  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: 19.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 23.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 22.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 53.97
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 0.24
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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=nicholasKluge/TeenyTinyLlama-160m
+      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: 36.92
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 42.63
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      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: 11.39
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
+      name: Open Portuguese LLM Leaderboard
 ---
 # TeenyTinyLlama-160m
 
@@ -224,4 +371,20 @@ This repository was built as part of the RAIES ([Rede de Inteligência Artificia
 
 ## License
 
-TeenyTinyLlama-160m is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
+TeenyTinyLlama-160m 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-160m)
+
+|          Metric          | Value  |
+|--------------------------|--------|
+|Average                   |**28.2**|
+|ENEM Challenge (No Images)|   19.24|
+|BLUEX (No Images)         |   23.09|
+|OAB Exams                 |   22.37|
+|Assin2 RTE                |   53.97|
+|Assin2 STS                |    0.24|
+|FaQuAD NLI                |   43.97|
+|HateBR Binary             |   36.92|
+|PT Hate Speech Binary     |   42.63|
+|tweetSentBR               |   11.39|
+