Spaces:

poltextlab
/

mores_demo

Sleeping

vkovacs commited on Jan 10

Commit

c1f3033

1 Parent(s): 56b1f1f

64 tokens might be enough for sentences

Files changed (1) hide show

app.py CHANGED Viewed

@@ -47,7 +47,7 @@ def predict(text, model_id, tokenizer_id):
     model.to(device)
     inputs = tokenizer(text,
-                       max_length=512,
                        truncation=True,
                        padding="do_not_pad",
                        return_tensors="pt").to(device)

     model.to(device)
     inputs = tokenizer(text,
+                       max_length=64,
                        truncation=True,
                        padding="do_not_pad",
                        return_tensors="pt").to(device)