TypeError: argument 'ids': 'list' object cannot be interpreted as an integer when lora training

hello, i meet the same question," text = self._tokenizer.decode(token_ids, skip_special_tokens=skip_special_tokens)
TypeError: argument ā€˜ids’: ā€˜list’ object cannot be interpreted as an integer"

i hope it will be helpful. my question is i forget add ā€œfor output in batch_outputs:ā€ :rofl:

//my code is as follows:

batch_outputs = model.generate(
input_ids=prompt_ids.input_ids,
…
)
for output in batch_outputs:
print("output is ",tokenizer.decode(output, skip_special_tokens=True))

1 Like