Adding the Open Portuguese LLM Leaderboard Evaluation Results

#2
Files changed (1) hide show
  1. README.md +139 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- license: mit
3
  language:
4
  - pt
 
5
  tags:
6
  - gervasio-pt*
7
  - gervasio-ptpt
@@ -18,6 +18,127 @@ tags:
18
  datasets:
19
  - PORTULAN/extraglue
20
  - PORTULAN/extraglue-instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  ---
22
  </br>
23
  </br>
@@ -172,4 +293,20 @@ grant PINFRA/22117/2016; research project GPT-PT - Transformer-based Decoder for
172
  grant CPCA-IAC/AV/478395/2022; innovation project
173
  ACCELERAT.AI - Multilingual Intelligent Contact Centers, funded by IAPMEI, I.P. - Agência para a Competitividade e Inovação
174
  under the grant C625734525-00462629, of Plano de Recuperação e Resiliência,
175
- call RE-C05-i01.01 – Agendas/Alianças Mobilizadoras para a Reindustrialização.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  language:
3
  - pt
4
+ license: mit
5
  tags:
6
  - gervasio-pt*
7
  - gervasio-ptpt
 
18
  datasets:
19
  - PORTULAN/extraglue
20
  - PORTULAN/extraglue-instruct
21
+ model-index:
22
+ - name: gervasio-7b-portuguese-ptbr-decoder
23
+ results:
24
+ - task:
25
+ type: text-generation
26
+ name: Text Generation
27
+ dataset:
28
+ name: ENEM Challenge (No Images)
29
+ type: eduagarcia/enem_challenge
30
+ split: train
31
+ args:
32
+ num_few_shot: 3
33
+ metrics:
34
+ - type: acc
35
+ value: 21.34
36
+ name: accuracy
37
+ source:
38
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
39
+ name: Open Portuguese LLM Leaderboard
40
+ - task:
41
+ type: text-generation
42
+ name: Text Generation
43
+ dataset:
44
+ name: BLUEX (No Images)
45
+ type: eduagarcia-temp/BLUEX_without_images
46
+ split: train
47
+ args:
48
+ num_few_shot: 3
49
+ metrics:
50
+ - type: acc
51
+ value: 21.0
52
+ name: accuracy
53
+ source:
54
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
55
+ name: Open Portuguese LLM Leaderboard
56
+ - task:
57
+ type: text-generation
58
+ name: Text Generation
59
+ dataset:
60
+ name: OAB Exams
61
+ type: eduagarcia/oab_exams
62
+ split: train
63
+ args:
64
+ num_few_shot: 3
65
+ metrics:
66
+ - type: acc
67
+ value: 26.29
68
+ name: accuracy
69
+ source:
70
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
71
+ name: Open Portuguese LLM Leaderboard
72
+ - task:
73
+ type: text-generation
74
+ name: Text Generation
75
+ dataset:
76
+ name: Assin2 RTE
77
+ type: assin2
78
+ split: test
79
+ args:
80
+ num_few_shot: 15
81
+ metrics:
82
+ - type: f1_macro
83
+ value: 83.15
84
+ name: f1-macro
85
+ - type: pearson
86
+ value: 69.55
87
+ name: pearson
88
+ source:
89
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
90
+ name: Open Portuguese LLM Leaderboard
91
+ - task:
92
+ type: text-generation
93
+ name: Text Generation
94
+ dataset:
95
+ name: FaQuAD NLI
96
+ type: ruanchaves/faquad-nli
97
+ split: test
98
+ args:
99
+ num_few_shot: 15
100
+ metrics:
101
+ - type: f1_macro
102
+ value: 18.59
103
+ name: f1-macro
104
+ source:
105
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
106
+ name: Open Portuguese LLM Leaderboard
107
+ - task:
108
+ type: text-generation
109
+ name: Text Generation
110
+ dataset:
111
+ name: HateBR Binary
112
+ type: eduagarcia/portuguese_benchmark
113
+ split: test
114
+ args:
115
+ num_few_shot: 25
116
+ metrics:
117
+ - type: f1_macro
118
+ value: 53.8
119
+ name: f1-macro
120
+ - type: f1_macro
121
+ value: 47.24
122
+ name: f1-macro
123
+ source:
124
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
125
+ name: Open Portuguese LLM Leaderboard
126
+ - task:
127
+ type: text-generation
128
+ name: Text Generation
129
+ dataset:
130
+ name: tweetSentBR
131
+ type: eduagarcia-temp/tweetsentbr
132
+ split: test
133
+ args:
134
+ num_few_shot: 25
135
+ metrics:
136
+ - type: f1_macro
137
+ value: 14.21
138
+ name: f1-macro
139
+ source:
140
+ url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=PORTULAN/gervasio-7b-portuguese-ptbr-decoder
141
+ name: Open Portuguese LLM Leaderboard
142
  ---
143
  </br>
144
  </br>
 
293
  grant CPCA-IAC/AV/478395/2022; innovation project
294
  ACCELERAT.AI - Multilingual Intelligent Contact Centers, funded by IAPMEI, I.P. - Agência para a Competitividade e Inovação
295
  under the grant C625734525-00462629, of Plano de Recuperação e Resiliência,
296
+ call RE-C05-i01.01 – Agendas/Alianças Mobilizadoras para a Reindustrialização.
297
+ # [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
298
+ 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)
299
+
300
+ | Metric | Value |
301
+ |--------------------------|---------|
302
+ |Average |**39.46**|
303
+ |ENEM Challenge (No Images)| 21.34|
304
+ |BLUEX (No Images) | 21|
305
+ |OAB Exams | 26.29|
306
+ |Assin2 RTE | 83.15|
307
+ |Assin2 STS | 69.55|
308
+ |FaQuAD NLI | 18.59|
309
+ |HateBR Binary | 53.80|
310
+ |PT Hate Speech Binary | 47.24|
311
+ |tweetSentBR | 14.21|
312
+