Spaces:
Running
Running
Upload leaderboard_data_20250413_002339.csv
Browse files
output/leaderboard_data_20250413_002339.csv
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
T,Modelo,Tipo,Arquitetura,Tipo de Peso,Precisão,Licença,#Params (B),Hub Likes,Disponível no hub,SHA do modelo,Média Geral,Área Médica,Área do Direito,Provas Militares,Computação,Discurso de Ódio,Economia e Contabilidade,Semântica e Inferência,Multidisciplinar,Revalida,MREX,OAB,ENAM,AFA,ITA,IME,POSCOMP,OBI,HateBR,PT Hate Speech,tweetSentBR,BCB,CFCES,FAQUAD NLI,ASSIN2 RTE,ASSIN2 STS,ENEM,BLUEX,CNPU,ENADE,BNDES,CACD (1ª fase),CACD (2ª fase),Datasets Área Médica,Datasets Área do Direito,Datasets Provas Militares,Datasets Computação,Datasets Discurso de Ódio,Datasets Economia e Contabilidade,Datasets Semântica e Inferência,Datasets Multidisciplinar,energy_dataset,reasoning_dataset
|
2 |
-
PT,openai/gpt2-portuguese,PT :
|
3 |
-
PT,rufimelo/bert-large-portuguese-cased,PT :
|
4 |
-
|
5 |
-
RL,brasileira/llama-2-7b-pt,RL :
|
6 |
-
PT,neuralmind/bert-base-portuguese-cased,PT :
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
PT,saramago/roberta-base-portuguese,PT :
|
12 |
-
|
13 |
-
PT,nlp-wyldlab/deberta-v3-base-portuguese,PT :
|
|
|
1 |
T,Modelo,Tipo,Arquitetura,Tipo de Peso,Precisão,Licença,#Params (B),Hub Likes,Disponível no hub,SHA do modelo,Média Geral,Área Médica,Área do Direito,Provas Militares,Computação,Discurso de Ódio,Economia e Contabilidade,Semântica e Inferência,Multidisciplinar,Revalida,MREX,OAB,ENAM,AFA,ITA,IME,POSCOMP,OBI,HateBR,PT Hate Speech,tweetSentBR,BCB,CFCES,FAQUAD NLI,ASSIN2 RTE,ASSIN2 STS,ENEM,BLUEX,CNPU,ENADE,BNDES,CACD (1ª fase),CACD (2ª fase),Datasets Área Médica,Datasets Área do Direito,Datasets Provas Militares,Datasets Computação,Datasets Discurso de Ódio,Datasets Economia e Contabilidade,Datasets Semântica e Inferência,Datasets Multidisciplinar,energy_dataset,reasoning_dataset
|
2 |
+
PT,openai/gpt2-portuguese,PT : Pre trained,,Original,float16,MIT,0.12,268,True,42b7792,0.71,0.62,0.67,0.59,0.73,0.75,0.85,0.78,0.71,0.60,0.63,0.66,0.68,0.57,0.57,0.62,0.70,0.77,0.77,0.71,0.77,0.89,0.80,0.78,0.74,0.81,0.69,0.71,0.71,0.73,0.65,0.73,0.74,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
3 |
+
PT,rufimelo/bert-large-portuguese-cased,PT : Pre trained,,Original,bfloat16,MIT,0.34,96,True,b1f4531,0.77,0.76,0.97,0.97,0.69,0.89,0.68,0.77,0.61,0.80,0.72,0.99,0.96,0.93,0.99,0.99,0.70,0.67,0.88,0.87,0.91,0.66,0.70,0.78,0.79,0.75,0.66,0.66,0.58,0.58,0.66,0.60,0.56,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
4 |
+
SFT,unicamp-dl/mbert-portuguese-lener,SFT : Supervised Finetuning,,Original,float16,Apache-2.0,0.11,89,True,a764b32,0.52,0.47,0.65,0.48,0.63,0.57,0.55,0.67,0.40,0.45,0.49,0.63,0.67,0.48,0.49,0.45,0.60,0.67,0.57,0.58,0.55,0.59,0.50,0.68,0.72,0.61,0.39,0.38,0.42,0.37,0.44,0.41,0.41,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
5 |
+
RL,brasileira/llama-2-7b-pt,RL : Reinforcement Learning,,Original,bfloat16,LLAMA 2,7.0,562,True,c24dd37,0.72,0.99,0.63,0.67,0.81,0.72,0.89,0.62,0.65,0.99,0.99,0.60,0.65,0.73,0.64,0.64,0.83,0.79,0.74,0.74,0.68,0.92,0.86,0.64,0.63,0.60,0.68,0.71,0.60,0.64,0.69,0.65,0.62,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
6 |
+
PT,neuralmind/bert-base-portuguese-cased,PT : Pre trained,,Original,float16,MIT,0.11,153,True,main,0.79,0.75,0.79,0.60,0.83,0.83,0.62,0.74,0.92,0.73,0.77,0.73,0.85,0.57,0.59,0.64,0.84,0.82,0.90,0.82,0.76,0.68,0.57,0.76,0.72,0.75,0.95,0.93,0.88,0.91,0.92,0.94,0.93,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
7 |
+
SFT,tulioandrade/mistral-7b-pt-adapter,SFT : Supervised Finetuning,,Adapter,bfloat16,Apache-2.0,7.2,315,True,main,0.70,0.53,0.67,0.52,0.60,0.59,0.63,0.93,0.84,0.55,0.52,0.64,0.70,0.52,0.50,0.52,0.61,0.60,0.57,0.59,0.61,0.62,0.64,0.94,0.90,0.94,0.80,0.88,0.83,0.89,0.80,0.89,0.81,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
8 |
+
SFT,PetroNLP/xlm-roberta-large-portuguese-instruct,SFT : Supervised Finetuning,,Original,bfloat16,Apache-2.0,0.56,173,True,8a67c19,0.62,0.55,0.48,0.73,0.87,0.75,0.75,0.46,0.52,0.52,0.59,0.48,0.48,0.68,0.75,0.77,0.89,0.85,0.77,0.68,0.81,0.71,0.80,0.51,0.46,0.42,0.54,0.48,0.50,0.54,0.52,0.53,0.53,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
9 |
+
SFT,pucpr/biobertpt-bio,SFT : Supervised Finetuning,,Original,float16,CC-BY-SA-4.0,0.11,47,True,ab2d4b9,0.61,0.70,0.69,0.76,0.56,0.57,0.63,0.52,0.56,0.72,0.68,0.70,0.68,0.84,0.74,0.70,0.56,0.56,0.53,0.58,0.60,0.62,0.63,0.57,0.50,0.50,0.60,0.60,0.52,0.51,0.54,0.61,0.56,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
10 |
+
SFT,ai-forever/gpt-pequeno-pt,SFT : Supervised Finetuning,,Original,float16,MIT,1.3,409,True,main,0.75,0.87,0.83,0.72,0.56,0.78,0.83,0.81,0.70,0.94,0.80,0.82,0.85,0.76,0.71,0.69,0.56,0.56,0.83,0.74,0.76,0.78,0.88,0.80,0.86,0.78,0.67,0.68,0.70,0.70,0.74,0.73,0.70,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
11 |
+
PT,saramago/roberta-base-portuguese,PT : Pre trained,,Original,float16,MIT,0.13,112,True,main,0.93,0.62,0.99,0.96,0.91,0.89,0.95,0.97,0.99,0.62,0.62,0.99,0.99,0.96,0.94,0.96,0.96,0.87,0.92,0.86,0.90,0.94,0.96,0.99,0.99,0.94,0.98,0.99,0.99,0.99,0.99,0.99,0.99,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
12 |
+
SFT,pierreguillou/bert-base-brpt-clinical,SFT : Supervised Finetuning,,Original,float16,MIT,0.11,73,True,c7bef2a,0.55,0.40,0.70,0.61,0.67,0.63,0.48,0.52,0.48,0.38,0.43,0.69,0.70,0.62,0.58,0.63,0.71,0.63,0.63,0.62,0.64,0.50,0.45,0.50,0.54,0.53,0.46,0.47,0.50,0.47,0.48,0.48,0.52,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|
13 |
+
PT,nlp-wyldlab/deberta-v3-base-portuguese,PT : Pre trained,,Original,float16,MIT,0.18,128,True,main,0.75,0.59,0.67,0.83,0.68,0.78,0.88,0.72,0.75,0.58,0.61,0.70,0.64,0.79,0.89,0.81,0.65,0.71,0.82,0.77,0.74,0.85,0.91,0.69,0.69,0.79,0.76,0.82,0.69,0.77,0.69,0.75,0.78,\"Revalida, MREX\",\"OAB, ENAM\",\"AFA, ITA, IME\",\"POSCOMP, OBI\",\"HateBR, PT Hate Speech, tweetSentBR\",\"BCB, CFCES\",\"FAQUAD NLI, ASSIN2 RTE, ASSIN2 STS\",\"ENEM, BLUEX, CNPU, ENADE, BNDES, CACD (1ª fase), CACD (2ª fase)\",0.5,0.5
|