Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
|
|
20 |
# To get lang_id use any of ["<s>", "</s>", "<2acf>", "<2eng>", "<2bis>", "<2bzj>", "<2cbk>", "<2crs>", "<2djk>", "<2gul>", "<2hat>", "<2hwc>", "<2icr>", "<2jam>", "<2kri>", "<2ktu>", "<2mbf>", "<2mfe>", "<2mkn>", "<2pap>", "<2pcm>", "<2pis>", "<2rop>", "<2sag>", "<2srm>", "<2srn>", "<2tcs>", "<2tdt>", "<2tpi>"]
|
21 |
|
22 |
# First tokenize the input and outputs. The format below is how CreoleM2M was trained so the input should be "Sentence </s> <2xxx>" where xxx is the language code. Similarly, the output should be "<2yyy> Sentence </s>".
|
23 |
-
inp = tokenizer('Wen dey wen stretch him out fo whip him real hard , Paul wen tell da captain dat stay dea ,
|
24 |
|
25 |
model.eval() # Set dropouts to zero
|
26 |
|
|
|
20 |
# To get lang_id use any of ["<s>", "</s>", "<2acf>", "<2eng>", "<2bis>", "<2bzj>", "<2cbk>", "<2crs>", "<2djk>", "<2gul>", "<2hat>", "<2hwc>", "<2icr>", "<2jam>", "<2kri>", "<2ktu>", "<2mbf>", "<2mfe>", "<2mkn>", "<2pap>", "<2pcm>", "<2pis>", "<2rop>", "<2sag>", "<2srm>", "<2srn>", "<2tcs>", "<2tdt>", "<2tpi>"]
|
21 |
|
22 |
# First tokenize the input and outputs. The format below is how CreoleM2M was trained so the input should be "Sentence </s> <2xxx>" where xxx is the language code. Similarly, the output should be "<2yyy> Sentence </s>".
|
23 |
+
inp = tokenizer('Wen dey wen stretch him out fo whip him real hard , Paul wen tell da captain dat stay dea , "Dis okay in da rules fo da Rome peopo ? fo you fo whip one guy dat get da same rights jalike da Rome peopo ? even one guy dat neva do notting wrong ?" </s> <2hwc>', add_special_tokens=False, return_tensors="pt", padding=True).input_ids
|
24 |
|
25 |
model.eval() # Set dropouts to zero
|
26 |
|