File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/run_captioning.py", line 102, in gen_json
captions = eval_model(args, model_name, tokenizer, model, image_processor, image_batch, qs=prompt, device="cuda")
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/run_captioning.py", line 93, in eval_model
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 348
5, in batch_decode
return [
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 348
6, in <listcomp>
self.decode(
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 352
5, in decode
return self._decode(
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/tokenization_utils.py", line 931, in
_decode
filtered_tokens = self.convert_ids_to_tokens(token_ids, skip_special_tokens=skip_special_tokens)
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/tokenization_utils.py", line 912, in
convert_ids_to_tokens
tokens.append(self._convert_id_to_token(index))
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py",
line 204, in _convert_id_to_token
token = self.sp_model.IdToPiece(index)
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/sentencepiece/__init__.py", line 1045, in _batched
_func
return _func(self, arg)
File "/home/ubuntu/wbc/captioning/InternLM-XComposer/projects/ShareGPT4V/caption/lib/python3.10/site-packages/sentencepiece/__init__.py", line 1038, in _func
raise IndexError('piece id is out of range.')
IndexError: piece id is out of range.
Hitting this issue when decoding: any thoughts?