Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
datasets:
|
4 |
-
-
|
5 |
- jerteh/SrpWiki
|
6 |
- jerteh/SrpELTeC
|
7 |
-
-
|
8 |
language:
|
9 |
- sr
|
10 |
tags:
|
@@ -14,9 +14,111 @@ tags:
|
|
14 |
- BERT
|
15 |
- MaskedLM
|
16 |
---
|
17 |
-
Mali enkoderski model za srpski jezik.
|
18 |
|
19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
kao i korpus [PDRS 1.0](https://www.clarin.si/repository/xmlui/handle/11356/1752) razvijen od strane Instituta za Srpski jezik SANU.
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
datasets:
|
4 |
+
- jerteh/cc100-sr-jerteh
|
5 |
- jerteh/SrpWiki
|
6 |
- jerteh/SrpELTeC
|
7 |
+
- srwac
|
8 |
language:
|
9 |
- sr
|
10 |
tags:
|
|
|
14 |
- BERT
|
15 |
- MaskedLM
|
16 |
---
|
|
|
17 |
|
18 |
+
<h4><!--<i class="highlight-container"><b class="highlight">sr-gpt2-large</b></i> je sada -->
|
19 |
+
<i class="highlight-container"><b class="highlight">jerteh-125</b></i> —
|
20 |
+
BERT model specijalno obučen za srpski jezik.</h4>
|
21 |
+
|
22 |
+
<img src="cover.png" style="width:100%">
|
23 |
+
|
24 |
+
<div id="zastava">
|
25 |
+
<div class="grb">
|
26 |
+
<img src="https://www.ai.gov.rs/img/logo_60x120-2.png" style="position:relative; left:30px; z-index:10; height:85px">
|
27 |
+
</div>
|
28 |
+
<table width=100% style="border:0px">
|
29 |
+
<tr style="background-color:#C6363C;width:100%;border:0px;height:30px"><td></td></tr>
|
30 |
+
<tr style="background-color:#0C4076;width:100%;border:0px;height:30px"><td></td></tr>
|
31 |
+
<tr style="background-color:#ffffff;width:100%;border:0px;height:30px"><td></td></tr>
|
32 |
+
</table>
|
33 |
+
</div>
|
34 |
+
|
35 |
+
Vektorizuje reči, ili dopunjava nedostajuće reči u tekstu.
|
36 |
+
Jednaka podrška unosa i na ćirilici i na latinici!
|
37 |
+
|
38 |
+
Pored navedenih, model je obučavan i na ostalim korpusima [Društva za jezičke resurse i tehnologije](https://jerteh.rs),
|
39 |
+
uključujući korpuse savremenog srpskog jezika: SrpKor2013 i SrpKor2021,
|
40 |
kao i korpus [PDRS 1.0](https://www.clarin.si/repository/xmlui/handle/11356/1752) razvijen od strane Instituta za Srpski jezik SANU.
|
41 |
|
42 |
+
|
43 |
+
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
44 |
+
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Autor</div>
|
45 |
+
<a href="https://huggingface.co/procesaur">
|
46 |
+
<div class="flex">
|
47 |
+
<div
|
48 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
49 |
+
background-size: cover; background-image: url('https://cdn-uploads.huggingface.co/production/uploads/1673534533167-63bc254fb8c61b8aa496a39b.jpeg?w=200&h=200&f=face')">
|
50 |
+
</div>
|
51 |
+
</div>
|
52 |
+
</a>
|
53 |
+
<div style="text-align: center; font-size: 16px; font-weight: 800">Mihailo Škorić</div>
|
54 |
+
<div>
|
55 |
+
<a href="https://huggingface.co/procesaur">
|
56 |
+
<div style="text-align: center; font-size: 14px;">@procesaur</div>
|
57 |
+
</a>
|
58 |
+
</div>
|
59 |
+
</div>
|
60 |
+
|
61 |
+
<h4>U slučaju potrebe za većim modelom, pogledajte <a href="https://huggingface.co/jerteh/jerteh-355" class="highlight-container">
|
62 |
+
<b class="highlight">jerteh-355</b></a> — najveći BERT model za srpski jezik.</h4>
|
63 |
+
|
64 |
+
<h4>U slučaju potrebe za generativnim modelom, pogledajte <a href="https://huggingface.co/jerteh/gpt2-orao" class="highlight-container">
|
65 |
+
<b class="highlight">gpt2-orao</b></a> i <a href="https://huggingface.co/jerteh/gpt2-vrabac" class="highlight-container">
|
66 |
+
<b class="highlight">gpt2-vrabac</b></a></h4>
|
67 |
+
|
68 |
+
|
69 |
+
<style>
|
70 |
+
|
71 |
+
.highlight-container, .highlight {
|
72 |
+
position: relative;
|
73 |
+
text-decoration:none
|
74 |
+
}
|
75 |
+
|
76 |
+
.highlight-container {
|
77 |
+
display: inline-block;
|
78 |
+
|
79 |
+
}
|
80 |
+
|
81 |
+
.highlight{
|
82 |
+
color:white;
|
83 |
+
text-transform:uppercase;
|
84 |
+
font-size: 16pt;
|
85 |
+
|
86 |
+
}
|
87 |
+
|
88 |
+
.highlight-container{
|
89 |
+
padding:5px 10px
|
90 |
+
}
|
91 |
+
|
92 |
+
.highlight-container:before {
|
93 |
+
content: " ";
|
94 |
+
display: block;
|
95 |
+
height: 100%;
|
96 |
+
width: 100%;
|
97 |
+
margin-left: 0px;
|
98 |
+
margin-right: 0px;
|
99 |
+
position: absolute;
|
100 |
+
background: #e80909;
|
101 |
+
transform: rotate(2deg);
|
102 |
+
top: -1px;
|
103 |
+
left: -1px;
|
104 |
+
border-radius: 20% 25% 20% 24%;
|
105 |
+
padding: 10px 18px 18px 10px;
|
106 |
+
}
|
107 |
+
|
108 |
+
div.grb, #zastava>table {
|
109 |
+
position:absolute;
|
110 |
+
top:0px;
|
111 |
+
left: 0px;
|
112 |
+
margin:0px
|
113 |
+
}
|
114 |
+
|
115 |
+
div.grb>img, #zastava>table{
|
116 |
+
margin:0px
|
117 |
+
}
|
118 |
+
|
119 |
+
#zastava {
|
120 |
+
position: relative;
|
121 |
+
margin-bottom:120px
|
122 |
+
}
|
123 |
+
|
124 |
+
</style>
|