Hugging Face's logo

NatLibFi
/
FintoAI-data-YSO

Text Classification
Swedish
Finnish
English
glam
lam
subject indexing
annif
Model card Files Community
1
juhoinkinen commited on
Commit
a5af869
•
1 Parent(s): 8a0d3f9

Upload project(s) *-en with Annif

Browse files
Files changed (9) hide show
  1. .gitattributes +4 -0
  2. projects/yso-bonsai-en.zip +3 -0
  3. projects/yso-en.zip +3 -0
  4. projects/yso-fasttext-en.zip +3 -0
  5. projects/yso-mllm-en.zip +3 -0
  6. yso-bonsai-en.cfg +15 -0
  7. yso-en.cfg +11 -0
  8. yso-fasttext-en.cfg +19 -0
  9. yso-mllm-en.cfg +10 -0
.gitattributes CHANGED
@@ -7,3 +7,7 @@ projects/yso-mllm-sv.zip filter=lfs diff=lfs merge=lfs -text
7
  projects/yso-bonsai-sv.zip filter=lfs diff=lfs merge=lfs -text
8
  projects/yso-fasttext-sv.zip filter=lfs diff=lfs merge=lfs -text
9
  projects/yso-sv.zip filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
7
  projects/yso-bonsai-sv.zip filter=lfs diff=lfs merge=lfs -text
8
  projects/yso-fasttext-sv.zip filter=lfs diff=lfs merge=lfs -text
9
  projects/yso-sv.zip filter=lfs diff=lfs merge=lfs -text
10
+ projects/yso-bonsai-en.zip filter=lfs diff=lfs merge=lfs -text
11
+ projects/yso-en.zip filter=lfs diff=lfs merge=lfs -text
12
+ projects/yso-mllm-en.zip filter=lfs diff=lfs merge=lfs -text
13
+ projects/yso-fasttext-en.zip filter=lfs diff=lfs merge=lfs -text
projects/yso-bonsai-en.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e853e059e93a738a9c2e2d0dce745d5548cc17cf20ea292c8a0eaf48c824187a
3
+ size 1647905019
projects/yso-en.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d80802a3ea051e0467f0234dc702c252cf714c96bd6cda5fb74df87edcd3ac
3
+ size 185711127
projects/yso-fasttext-en.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85648952f595451f6812836e527dd39ebce2b8a83c1ab7d7f0b36014aa9f8dba
3
+ size 3839436332
projects/yso-mllm-en.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408482ea581704f6113298ab5527575db7ce49bb315d2ba95a3362eb603a173f
3
+ size 2114994
yso-bonsai-en.cfg ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [yso-bonsai-en]
2
+ name = YSO Omikuji Bonsai English
3
+ language = en
4
+ backend = omikuji
5
+ analyzer = simple
6
+ vocab = yso
7
+ cluster_balanced = False
8
+ cluster_k = 100
9
+ max_depth = 3
10
+ min_df = 5
11
+ ngram = 2
12
+ limit = 1000
13
+ transform = limit(5000)
14
+ access = hidden
15
+
yso-en.cfg ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [yso-en]
2
+ name = YSO English (2022-11-02)
3
+ language = en
4
+ backend = nn_ensemble
5
+ sources = yso-mllm-en:0.3426,yso-fasttext-en:0.1419,yso-bonsai-en:0.5155
6
+ limit = 100
7
+ vocab = yso
8
+ nodes = 100
9
+ dropout_rate = 0.2
10
+ epochs = 10
11
+
yso-fasttext-en.cfg ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [yso-fasttext-en]
2
+ name = YSO fastText English
3
+ language = en
4
+ backend = fasttext
5
+ analyzer = snowball(english)
6
+ dim = 430
7
+ lr = 0.506539
8
+ epoch = 115
9
+ minn = 4
10
+ maxn = 5
11
+ mincount = 1
12
+ wordngrams = 2
13
+ loss = hs
14
+ limit = 1000
15
+ chunksize = 24
16
+ vocab = yso
17
+ transform = limit(15000),filter_lang,limit(5000)
18
+ access = hidden
19
+
yso-mllm-en.cfg ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ [yso-mllm-en]
2
+ name = YSO MLLM English
3
+ language = en
4
+ backend = mllm
5
+ analyzer = snowball(english)
6
+ vocab = yso
7
+ limit = 1000
8
+ transform = limit(2500000)
9
+ access = hidden
10
+