Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
|
5 |
+
--------------------------------------------------------------------------------------------------
|
6 |
+
|
7 |
+
<body>
|
8 |
+
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
|
9 |
+
<br>
|
10 |
+
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
|
11 |
+
<br>
|
12 |
+
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: MiniLM</span>
|
13 |
+
<br>
|
14 |
+
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
|
15 |
+
<br>
|
16 |
+
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
|
17 |
+
<br>
|
18 |
+
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
|
19 |
+
</body>
|
20 |
+
|
21 |
+
--------------------------------------------------------------------------------------------------
|
22 |
+
|
23 |
+
<h3>Model description</h3>
|
24 |
+
|
25 |
+
This is a <b>MiniLMv2</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using <b>mMiniLMv2</b> ([L6xH384 mMiniLMv2](https://github.com/microsoft/unilm/tree/master/minilm)) as a starting point and focusing it on the Italian language by modifying the embedding layer
|
26 |
+
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
|
27 |
+
|
28 |
+
The resulting model has 23M parameters, a vocabulary of 30.498 tokens, and a size of ~90 MB.
|
29 |
+
|
30 |
+
<h3>References</h3>
|
31 |
+
|
32 |
+
[1] https://arxiv.org/abs/2012.15828
|
33 |
+
|
34 |
+
[2] https://arxiv.org/abs/2010.05609
|
35 |
+
|
36 |
+
<h3>License</h3>
|
37 |
+
|
38 |
+
The model is released under <b>MIT</b> license
|