File size: 283 Bytes
5fa1a76 |
1 2 3 4 5 6 7 |
model_inputs = tokenizer(
["1, 2, 3", "A, B, C, D, E"], padding=True, return_tensors="pt"
).to("cuda")
generated_ids = model.generate(**model_inputs)
tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'1, 2, 33333333333'
With left-padding, it works as expected! |