Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,7 +1,7 @@
 ---
-license: mit
 language:
 - pt
+license: mit
 tags:
 - gervasio-pt*
 - gervasio-ptpt
@@ -18,6 +18,127 @@ tags:
 datasets:
 - PORTULAN/extraglue
 - PORTULAN/extraglue-instruct
+model-index:
+- name: gervasio-7b-portuguese-ptbr-decoder
+  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: 21.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      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: 21.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      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: 26.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      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: 83.15
+      name: f1-macro
+    - type: pearson
+      value: 69.55
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      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: 18.59
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HateBR Binary
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 53.8
+      name: f1-macro
+    - type: f1_macro
+      value: 47.24
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      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: 14.21
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+      name: Open Portuguese LLM Leaderboard
 ---
 </br>
 </br>
@@ -172,4 +293,20 @@ grant PINFRA/22117/2016; research project GPT-PT - Transformer-based Decoder for
 grant CPCA-IAC/AV/478395/2022; innovation project 
 ACCELERAT.AI - Multilingual Intelligent Contact Centers, funded by IAPMEI, I.P. - Agência para a Competitividade e Inovação 
 under the grant C625734525-00462629, of Plano de Recuperação e Resiliência, 
-call RE-C05-i01.01 – Agendas/Alianças Mobilizadoras para a Reindustrialização.
+call RE-C05-i01.01 – Agendas/Alianças Mobilizadoras para a Reindustrialização.
+# [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/PORTULAN/gervasio-7b-portuguese-ptbr-decoder)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**39.46**|
+|ENEM Challenge (No Images)|    21.34|
+|BLUEX (No Images)         |       21|
+|OAB Exams                 |    26.29|
+|Assin2 RTE                |    83.15|
+|Assin2 STS                |    69.55|
+|FaQuAD NLI                |    18.59|
+|HateBR Binary             |    53.80|
+|PT Hate Speech Binary     |    47.24|
+|tweetSentBR               |    14.21|
+