You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
--save file - write serialized models on disk after training and before generating the data; the user can set --limit to 0 to only train the models and save them without proceeding to data generation;
--load file - instead of training the models, load the prepared models from the file and start generating the data.
Serialization format: one byte for version (equals to 0), then simple binary serialization of all the models; the whole file is compressed with ZSTD level 1 using CompressedWriteBuffer (no need to allow any compression options to choose).
The text was updated successfully, but these errors were encountered:
Use case
Generate models once and reuse them.
Describe the solution you'd like
Add command line options:
Serialization format: one byte for version (equals to 0), then simple binary serialization of all the models; the whole file is compressed with ZSTD level 1 using CompressedWriteBuffer (no need to allow any compression options to choose).
The text was updated successfully, but these errors were encountered: