Hugging Face's logo

RenatoBarreira
/
BERT-VI

Text Classification
BERTopic
PyTorch
Portuguese
bert
bertimbau
Eval Results
Model card Files Community
RenatoBarreira commited on
Commit
ff64877
·
verified ·
1 Parent(s): b9352a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +227 -9
README.md CHANGED
@@ -14,17 +14,235 @@ model-index:
14
  - name: Bert-Vi
15
  results:
16
  - task:
17
- type: text-classification
18
  dataset:
19
- name: ai2_arc
20
- type: ai2_arc
21
  metrics:
22
- - name: AI2 Reasoning Challenge (25-Shot)
23
- type: AI2 Reasoning Challenge (25-Shot)
24
- value: 64.59
25
- source:
26
- name: Open LLM Leaderboard
27
- url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  pipeline_tag: text-classification
29
  library_name: bertopic
30
  ---
 
14
  - name: Bert-Vi
15
  results:
16
  - task:
17
+ type: text-classfication
18
  dataset:
19
+ type: RenatoBarreira/BERT-Vi_Trainning_data
20
+ name: 6000augaug
21
  metrics:
22
+ - name: pass@1
23
+ type: pass@1
24
+ value: 0.408
25
+ verified: false
26
+ - task:
27
+ type: text-generation
28
+ dataset:
29
+ type: openai_humaneval
30
+ name: HumanEval
31
+ metrics:
32
+ - name: pass@1
33
+ type: pass@1
34
+ value: 0.336
35
+ verified: false
36
+ - task:
37
+ type: text-generation
38
+ dataset:
39
+ type: mbpp
40
+ name: MBPP
41
+ metrics:
42
+ - name: pass@1
43
+ type: pass@1
44
+ value: 0.527
45
+ verified: false
46
+ - task:
47
+ type: text-generation
48
+ dataset:
49
+ type: ds1000
50
+ name: DS-1000 (Overall Completion)
51
+ metrics:
52
+ - name: pass@1
53
+ type: pass@1
54
+ value: 0.26
55
+ verified: false
56
+ - task:
57
+ type: text-generation
58
+ dataset:
59
+ type: nuprl/MultiPL-E
60
+ name: MultiPL-HumanEval (C++)
61
+ metrics:
62
+ - name: pass@1
63
+ type: pass@1
64
+ value: 0.3155
65
+ verified: false
66
+ - task:
67
+ type: text-generation
68
+ dataset:
69
+ type: nuprl/MultiPL-E
70
+ name: MultiPL-HumanEval (C#)
71
+ metrics:
72
+ - name: pass@1
73
+ type: pass@1
74
+ value: 0.2101
75
+ verified: false
76
+ - task:
77
+ type: text-generation
78
+ dataset:
79
+ type: nuprl/MultiPL-E
80
+ name: MultiPL-HumanEval (D)
81
+ metrics:
82
+ - name: pass@1
83
+ type: pass@1
84
+ value: 0.1357
85
+ verified: false
86
+ - task:
87
+ type: text-generation
88
+ dataset:
89
+ type: nuprl/MultiPL-E
90
+ name: MultiPL-HumanEval (Go)
91
+ metrics:
92
+ - name: pass@1
93
+ type: pass@1
94
+ value: 0.1761
95
+ verified: false
96
+ - task:
97
+ type: text-generation
98
+ dataset:
99
+ type: nuprl/MultiPL-E
100
+ name: MultiPL-HumanEval (Java)
101
+ metrics:
102
+ - name: pass@1
103
+ type: pass@1
104
+ value: 0.3022
105
+ verified: false
106
+ - task:
107
+ type: text-generation
108
+ dataset:
109
+ type: nuprl/MultiPL-E
110
+ name: MultiPL-HumanEval (Julia)
111
+ metrics:
112
+ - name: pass@1
113
+ type: pass@1
114
+ value: 0.2302
115
+ verified: false
116
+ - task:
117
+ type: text-generation
118
+ dataset:
119
+ type: nuprl/MultiPL-E
120
+ name: MultiPL-HumanEval (JavaScript)
121
+ metrics:
122
+ - name: pass@1
123
+ type: pass@1
124
+ value: 0.3079
125
+ verified: false
126
+ - task:
127
+ type: text-generation
128
+ dataset:
129
+ type: nuprl/MultiPL-E
130
+ name: MultiPL-HumanEval (Lua)
131
+ metrics:
132
+ - name: pass@1
133
+ type: pass@1
134
+ value: 0.2389
135
+ verified: false
136
+ - task:
137
+ type: text-generation
138
+ dataset:
139
+ type: nuprl/MultiPL-E
140
+ name: MultiPL-HumanEval (PHP)
141
+ metrics:
142
+ - name: pass@1
143
+ type: pass@1
144
+ value: 0.2608
145
+ verified: false
146
+ - task:
147
+ type: text-generation
148
+ dataset:
149
+ type: nuprl/MultiPL-E
150
+ name: MultiPL-HumanEval (Perl)
151
+ metrics:
152
+ - name: pass@1
153
+ type: pass@1
154
+ value: 0.1734
155
+ verified: false
156
+ - task:
157
+ type: text-generation
158
+ dataset:
159
+ type: nuprl/MultiPL-E
160
+ name: MultiPL-HumanEval (Python)
161
+ metrics:
162
+ - name: pass@1
163
+ type: pass@1
164
+ value: 0.3357
165
+ verified: false
166
+ - task:
167
+ type: text-generation
168
+ dataset:
169
+ type: nuprl/MultiPL-E
170
+ name: MultiPL-HumanEval (R)
171
+ metrics:
172
+ - name: pass@1
173
+ type: pass@1
174
+ value: 0.155
175
+ verified: false
176
+ - task:
177
+ type: text-generation
178
+ dataset:
179
+ type: nuprl/MultiPL-E
180
+ name: MultiPL-HumanEval (Ruby)
181
+ metrics:
182
+ - name: pass@1
183
+ type: pass@1
184
+ value: 0.0124
185
+ verified: false
186
+ - task:
187
+ type: text-generation
188
+ dataset:
189
+ type: nuprl/MultiPL-E
190
+ name: MultiPL-HumanEval (Racket)
191
+ metrics:
192
+ - name: pass@1
193
+ type: pass@1
194
+ value: 0.0007
195
+ verified: false
196
+ - task:
197
+ type: text-generation
198
+ dataset:
199
+ type: nuprl/MultiPL-E
200
+ name: MultiPL-HumanEval (Rust)
201
+ metrics:
202
+ - name: pass@1
203
+ type: pass@1
204
+ value: 0.2184
205
+ verified: false
206
+ - task:
207
+ type: text-generation
208
+ dataset:
209
+ type: nuprl/MultiPL-E
210
+ name: MultiPL-HumanEval (Scala)
211
+ metrics:
212
+ - name: pass@1
213
+ type: pass@1
214
+ value: 0.2761
215
+ verified: false
216
+ - task:
217
+ type: text-generation
218
+ dataset:
219
+ type: nuprl/MultiPL-E
220
+ name: MultiPL-HumanEval (Bash)
221
+ metrics:
222
+ - name: pass@1
223
+ type: pass@1
224
+ value: 0.1046
225
+ verified: false
226
+ - task:
227
+ type: text-generation
228
+ dataset:
229
+ type: nuprl/MultiPL-E
230
+ name: MultiPL-HumanEval (Swift)
231
+ metrics:
232
+ - name: pass@1
233
+ type: pass@1
234
+ value: 0.2274
235
+ verified: false
236
+ - task:
237
+ type: text-generation
238
+ dataset:
239
+ type: nuprl/MultiPL-E
240
+ name: MultiPL-HumanEval (TypeScript)
241
+ metrics:
242
+ - name: pass@1
243
+ type: pass@1
244
+ value: 0.3229
245
+ verified: false
246
  pipeline_tag: text-classification
247
  library_name: bertopic
248
  ---