Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
license: cc-by-sa-4.0
|
3 |
datasets:
|
4 |
- JeRTeh/cc100-sr-jerteh
|
5 |
- JeRTeh/SrpELTeC
|
@@ -14,18 +13,30 @@ tags:
|
|
14 |
- generisanje
|
15 |
---
|
16 |
|
17 |
-
Najveći generativni model za srpski jezik.
|
18 |
|
19 |
-
|
|
|
|
|
20 |
|
21 |
-
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Upotreba
|
25 |
|
26 |
```python
|
27 |
>>> from transformers import pipeline, set_seed
|
28 |
-
>>> generator = pipeline('text-generation', model='
|
29 |
>>> set_seed(23)
|
30 |
>>> generator("", max_length=30, num_return_sequences=5)
|
31 |
```
|
@@ -38,4 +49,82 @@ kao i korpus [PDRS 1.0](https://www.clarin.si/repository/xmlui/handle/11356/1752
|
|
38 |
{'generated_text': 'Iz tog razloga, na ovaj način se postiže bolja efikasnost rada, odnosno smanjuje se vreme potrebno za sprovođenje simulacije.'}]
|
39 |
```
|
40 |
|
41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
datasets:
|
3 |
- JeRTeh/cc100-sr-jerteh
|
4 |
- JeRTeh/SrpELTeC
|
|
|
13 |
- generisanje
|
14 |
---
|
15 |
|
|
|
16 |
|
17 |
+
<h4><i class="highlight-container"><b class="highlight">sr-gpt2-large</b></i> je sada
|
18 |
+
<i class="highlight-container"><b class="highlight">gpt2-orao</b></i> --
|
19 |
+
Najveći generativni model za srpski jezik.</h4>
|
20 |
|
21 |
+
<div id="zastava">
|
22 |
+
<div class="grb">
|
23 |
+
<img src="https://www.ai.gov.rs/img/logo_60x120-2.png" style="position:relative; left:30px; z-index:10; height:85px">
|
24 |
+
</div>
|
25 |
+
<table width=100% style="border:0px">
|
26 |
+
<tr style="background-color:#C6363C;width:100%;border:0px;height:30px"><td></td></tr>
|
27 |
+
<tr style="background-color:#0C4076;width:100%;border:0px;height:30px"><td></td></tr>
|
28 |
+
<tr style="background-color:#ffffff;width:100%;border:0px;height:30px"><td></td></tr>
|
29 |
+
</table>
|
30 |
+
</div>
|
31 |
+
|
32 |
+
Generiše novi tekst, ili nastavlja započeti tekstualni unos.\
|
33 |
+
Jednaka podrška unosa i na ćirilici i na latinici!
|
34 |
|
35 |
## Upotreba
|
36 |
|
37 |
```python
|
38 |
>>> from transformers import pipeline, set_seed
|
39 |
+
>>> generator = pipeline('text-generation', model='jerteh/gpt2-orao')
|
40 |
>>> set_seed(23)
|
41 |
>>> generator("", max_length=30, num_return_sequences=5)
|
42 |
```
|
|
|
49 |
{'generated_text': 'Iz tog razloga, na ovaj način se postiže bolja efikasnost rada, odnosno smanjuje se vreme potrebno za sprovođenje simulacije.'}]
|
50 |
```
|
51 |
|
52 |
+
Pored navedenih, model je obučavan i na ostalim korpusima [Društva za jezičke resurse i tehnologije](https://jerteh.rs), uključujući korpuse savremenog srpskog jezika: SrpKor2013 i SrpKor2021,
|
53 |
+
kao i korpus [PDRS 1.0](https://www.clarin.si/repository/xmlui/handle/11356/1752) razvijen od strane Instituta za Srpski jezik SANU.
|
54 |
+
|
55 |
+
<h4>U slučaju potrebe za manjim modelom, pogledajte <a href="https://huggingface.co/jerteh/gpt2-vrabac" class="highlight-container"><b class="highlight">gpt2-vrabac</b></a> --
|
56 |
+
manji model obučen na istom korpusu.</h4>
|
57 |
+
|
58 |
+
Modeli su obučavani na Nacionalnoj platformi za veštačku inteligenciju Srbije (sistem koji se bazira na nVidia DGX sistemima).
|
59 |
+
|
60 |
+
|
61 |
+
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
62 |
+
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Autor</div>
|
63 |
+
<a href="https://huggingface.co/procesaur">
|
64 |
+
<div class="flex">
|
65 |
+
<div
|
66 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
67 |
+
background-size: cover; background-image: url('https://cdn-uploads.huggingface.co/production/uploads/1673534533167-63bc254fb8c61b8aa496a39b.jpeg?w=200&h=200&f=face')">
|
68 |
+
</div>
|
69 |
+
</div>
|
70 |
+
</a>
|
71 |
+
<div style="text-align: center; font-size: 16px; font-weight: 800">Mihailo Škorić</div>
|
72 |
+
<div>
|
73 |
+
<a href="https://huggingface.co/procesaur">
|
74 |
+
<div style="text-align: center; font-size: 14px;">@procesaur</div>
|
75 |
+
</a>
|
76 |
+
</div>
|
77 |
+
</div>
|
78 |
+
|
79 |
+
|
80 |
+
<style>
|
81 |
+
|
82 |
+
.highlight-container, .highlight {
|
83 |
+
position: relative;
|
84 |
+
text-decoration:none
|
85 |
+
}
|
86 |
+
|
87 |
+
.highlight-container {
|
88 |
+
display: inline-block;
|
89 |
+
|
90 |
+
}
|
91 |
+
|
92 |
+
.highlight{
|
93 |
+
color:white;
|
94 |
+
text-transform:uppercase;
|
95 |
+
font-size: 16pt
|
96 |
+
}
|
97 |
+
|
98 |
+
.highlight-container:before {
|
99 |
+
content: " ";
|
100 |
+
display: block;
|
101 |
+
height: 110%;
|
102 |
+
width: 100%;
|
103 |
+
margin-left: 0px;
|
104 |
+
margin-right: 0px;
|
105 |
+
position: absolute;
|
106 |
+
background: #e80909;
|
107 |
+
transform: rotate(2deg);
|
108 |
+
top: -1px;
|
109 |
+
left: -1px;
|
110 |
+
border-radius: 20% 25% 20% 24%;
|
111 |
+
padding: 10px 3px 3px 10px;
|
112 |
+
}
|
113 |
+
|
114 |
+
div.grb, #zastava>table {
|
115 |
+
position:absolute;
|
116 |
+
top:0px;
|
117 |
+
left: 0px;
|
118 |
+
margin:0px
|
119 |
+
}
|
120 |
+
|
121 |
+
div.grb>img, #zastava>table{
|
122 |
+
margin:0px
|
123 |
+
}
|
124 |
+
|
125 |
+
#zastava {
|
126 |
+
position: relative;
|
127 |
+
margin-bottom:120px
|
128 |
+
}
|
129 |
+
|
130 |
+
</style>
|