FasterTransformer
FasterTransformer copied to clipboard
Can't run translate_example.py found in T5 model
Hello,
I am trying to run this file like mentioned here. https://github.com/NVIDIA/FasterTransformer/blob/main/docs/t5_guide.md. I got these errors. One of these is from building the project and I created an issue about it. Any help?
[The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'T5Tokenizer'.
The class this function is called from is 'PreTrainedTokenizerFast'.
2023-08-15 13:20:29,342 __main__ [INFO] Run gemm test: ./bin/t5_gemm 32 4 128 512 8 64 2048 512 8 64 2048 32128 0 1 0 > .tmp_gemm.log
2023-08-15 13:20:44,859 __main__ [INFO] Run gemm test: ./bin/t5_gemm 32 1 128 512 8 64 2048 512 8 64 2048 32128 0 1 1 > .tmp_gemm.log
[INFO] MPI is not available in this PyTorch build.
[INFO] MPI is not available in this PyTorch build.
[INFO] MPI is not available in this PyTorch build.
Traceback (most recent call last):
File "/content/FasterTransformer/examples/pytorch/t5/translate_example.py", line 507, in <module>
translate(vars(args))
File "/content/FasterTransformer/examples/pytorch/t5/translate_example.py", line 310, in translate
ft_encoder = FTT5Encoder(ft_encoder_weight.w, lib_path, encoder_config.num_heads,
File "/content/FasterTransformer/examples/pytorch/t5/../../../examples/pytorch/t5/utils/ft_encoder.py", line 380, in __init__
torch.classes.load_library(lib_path)
File "/usr/local/lib/python3.10/dist-packages/torch/_classes.py", line 51, in load_library
torch.ops.load_library(path)
File "/usr/local/lib/python3.10/dist-packages/torch/_ops.py", line 643, in load_library
ctypes.CDLL(path)
File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__
self._handle = _dlopen(self._name, mode)
OSError: /content/lib/libth_transformer.so: cannot open shared object file: No such file or directory]