English
word2vec
lbourdois commited on
Commit
c11f77f
1 Parent(s): 5014041

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -7,14 +7,14 @@ license: cc-by-4.0
7
  ---
8
 
9
  ## Information
10
- A word2vec model trained by Andrey Kutuzov (andreku@ifi.uio.no) on a vocabulary of size 273992 corresponding to 2252637050 tokens from the dataset `English_Wikipedia_Dump_of_February_2017`.
11
  The model is trained with the following properties: lemmatization and postag with the algorith Gensim Continuous Skipgram with window of 5 and dimension of 300.
12
 
13
  ## How to use?
14
  ```
15
  from gensim.models import KeyedVectors
16
  from huggingface_hub import hf_hub_download
17
- model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/eng_lem_postag_300_cont_skip_5_English_Wikipedia_Dump_of_February_2017", filename="model.bin"), binary=True, unicode_errors="ignore")
18
  ```
19
 
20
  ## Citation
 
7
  ---
8
 
9
  ## Information
10
+ A word2vec model trained by Andrey Kutuzov (andreku@ifi.uio.no) on a vocabulary of size 302866 corresponding to 2252637050 tokens from the dataset `English_Wikipedia_Dump_of_February_2017`.
11
  The model is trained with the following properties: lemmatization and postag with the algorith Gensim Continuous Skipgram with window of 5 and dimension of 300.
12
 
13
  ## How to use?
14
  ```
15
  from gensim.models import KeyedVectors
16
  from huggingface_hub import hf_hub_download
17
+ model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_5", filename="model.bin"), binary=True, unicode_errors="ignore")
18
  ```
19
 
20
  ## Citation