5w4n commited on
Commit
fc19172
1 Parent(s): 52f4fdb

Add cohere multilingual tokenizer

Browse files
Files changed (2) hide show
  1. app.py +1 -0
  2. dataset.csv +0 -0
app.py CHANGED
@@ -40,6 +40,7 @@ tokenizer_names_to_test = [
40
  "facebook/mbart-large-50",
41
  "EleutherAI/gpt-neox-20b",
42
  "simbolo-ai/multilingual-partial-syllable-tokenizer",
 
43
  ]
44
 
45
  with st.sidebar:
 
40
  "facebook/mbart-large-50",
41
  "EleutherAI/gpt-neox-20b",
42
  "simbolo-ai/multilingual-partial-syllable-tokenizer",
43
+ "Cohere/multilingual-22-12",
44
  ]
45
 
46
  with st.sidebar:
dataset.csv CHANGED
The diff for this file is too large to render. See raw diff