Files
axolotl/src/axolotl/utils/collators/__init__.py
Dan Saunders 231a67e70b Streaming SFT support (#3101)
* working

* fixes

* deprecate --iterable; cleanup

* pretrain_multipack_buffer_size -> streaming_multipack_buffer_size

* improvements

* tests

* remove unused

* docs, examples

* nit

* nit

* add val_set_size validation

* val

* nit

* min

* coderabbito

* cleanup

* nit

* add depr warning, cleanup

* nit

* fix test, fix quarto

* fix

* review comments

* review comments

* fix
2025-09-02 12:08:44 -04:00

18 lines
502 B
Python

"""Shared axolotl collators for multipacking, mamba, multimodal."""
from .batching import (
BatchSamplerDataCollatorForSeq2Seq,
DataCollatorForSeq2Seq,
PretrainingBatchSamplerDataCollatorForSeq2Seq,
V2BatchSamplerDataCollatorForSeq2Seq,
)
from .mamba import MambaDataCollator
__all__ = [
"DataCollatorForSeq2Seq",
"BatchSamplerDataCollatorForSeq2Seq",
"V2BatchSamplerDataCollatorForSeq2Seq",
"PretrainingBatchSamplerDataCollatorForSeq2Seq",
"MambaDataCollator",
]