update readme

README.md

@@ -22,9 +22,9 @@ Size of this model is __large__
 
 | Parameter      | Value        |
 |----------------|--------------|
-| Dimensionality | 100          |
-| Window Size    | 5            |
-| Epochs         | 10           |
+| Dimensionality | 300          |
+| Window Size    | 10           |
+| Epochs         | 20           |
 | Algorithm      | CBOW         |
 
 ## Versions
@@ -76,28 +76,28 @@ Once the model is loaded, you can use it as shown:
 
 ```python
 model.wv.most_similar("bendo")
-[('binks', 0.8920747637748718),
- ('bando', 0.8460732698440552),
- ('hood', 0.8299438953399658),
- ('tieks', 0.8264378309249878),
- ('hall', 0.817583441734314),
- ('secteur', 0.8145656585693359),
- ('barrio', 0.809047281742096),
- ('block', 0.793493390083313),
- ('bâtiment', 0.7826434969902039),
- ('bloc', 0.7753982543945312)]
+[('binks', 0.7082766890525818),
+ ('bando', 0.684855043888092),
+ ('tieks', 0.664956271648407),
+ ('hall', 0.6226587295532227),
+ ('ghetto', 0.6097022294998169),
+ ('barrio', 0.5864858627319336),
+ ('hood', 0.5714126229286194),
+ ('block', 0.5666197538375854),
+ ('quartier', 0.557117760181427),
+ ('bloc', 0.5540688037872314)]
 
 model.wv.most_similar("kichta")
-[('liasse', 0.878665566444397),
- ('sse-lia', 0.8552991151809692),
- ('kishta', 0.8535938262939453),
- ('kich', 0.7646669149398804),
- ('skalape', 0.7576569318771362),
- ('moula', 0.7466527223587036),
- ('valise', 0.7429592609405518),
- ('sacoche', 0.7324921488761902),
- ('mallette', 0.7247079014778137),
- ('re-pai', 0.7060815095901489)]
+[('liasse', 0.7318882942199707),
+ ('sse-lia', 0.7186722755432129),
+ ('kishta', 0.6604368686676025),
+ ('kich', 0.6188479661941528),
+ ('moula', 0.570914626121521),
+ ('sacoche', 0.553415834903717),
+ ('skalape', 0.5243070125579834),
+ ('Kichta', 0.49806657433509827),
+ ('ppe-fra', 0.49229520559310913),
+ ('valise', 0.49089524149894714)]
 ```
 
 2. **To find the word that doesn't match in a list of words**
@@ -114,10 +114,10 @@ model.wv.doesnt_match(["Zidane","Mbappé","Ronaldo","Messi","Jordan"])
 
 ```python
 model.wv.similarity("kichta", "moula")
-0.7466528
+0.57091457
 
 model.wv.similarity("bonheur", "moula")
-0.16985293
+0.09769239
 ```
 
 4. **Or even get the vector representation of a word**