mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 00:21:07 +01:00
Summary: When language models use c++ tokenizer, outputs are a c++ strings that are not necessarily valid utf-8 encodings. Default pybind11 casting uses strict utf-8 decoding. We relax the decoding using 'ignore' argument. Test Plan: https://www.internalfb.com/intern/testinfra/testrun/6473924609918070 Reviewed By: Nayef211 Differential Revision: D43970697 Pull Request resolved: https://github.com/pytorch/pytorch/pull/97282 Approved by: https://github.com/davidberard98 |
||
|---|---|---|
| .. | ||
| init.cpp | ||
| init.h | ||
| module_python.h | ||
| pybind_utils.cpp | ||
| pybind_utils.h | ||
| pybind.h | ||
| python_arg_flatten.cpp | ||
| python_arg_flatten.h | ||
| python_custom_class.cpp | ||
| python_custom_class.h | ||
| python_dict.cpp | ||
| python_dict.h | ||
| python_interpreter.cpp | ||
| python_ir.cpp | ||
| python_ir.h | ||
| python_ivalue.h | ||
| python_list.cpp | ||
| python_list.h | ||
| python_sugared_value.cpp | ||
| python_sugared_value.h | ||
| python_tracer.cpp | ||
| python_tracer.h | ||
| python_tree_views.cpp | ||
| python_tree_views.h | ||
| script_init.cpp | ||
| script_init.h | ||
| update_graph_executor_opt.cpp | ||
| update_graph_executor_opt.h | ||
| utf8_decoding_ignore.cpp | ||
| utf8_decoding_ignore.h | ||