diff --git a/convert-pt-to-ggml.py b/convert-pt-to-ggml.py index 22bd12e5c84..9e9b2dcebef 100644 --- a/convert-pt-to-ggml.py +++ b/convert-pt-to-ggml.py @@ -271,7 +271,7 @@ def bytes_to_unicode(): fout.write(struct.pack("i", len(tokens))) for key in tokens: - text = bytearray([byte_decoder[c] for c in key]).decode('utf-8', errors='replace').encode('utf-8') + text = bytearray([byte_decoder[c] for c in key]) fout.write(struct.pack("i", len(text))) fout.write(text)