Sft flash mask

[wtmlon]

PR types

PR changes

Description

适配 flash mask 数据流，支持 SFT，DPO

[paddle-bot[bot]]

Thanks for your contribution!

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 2.94118% with 33 lines in your changes missing coverage. Please review.

Project coverage is 55.61%. Comparing base (3ebe938) to head (1f6bfd1). Report is 228 commits behind head on develop.

Files with missing lines	Patch %	Lines
paddlenlp/data/data_collator.py	0.00%	11 Missing :warning:
paddlenlp/trl/trl_data.py	0.00%	10 Missing :warning:
paddlenlp/datasets/zero_padding_dataset.py	0.00%	4 Missing :warning:
paddlenlp/trl/dpo_trainer.py	0.00%	4 Missing :warning:
paddlenlp/transformers/llama/fusion_ops.py	0.00%	2 Missing :warning:
paddlenlp/transformers/llama/modeling.py	33.33%	2 Missing :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## develop #8664 +/- ## =========================================== - Coverage 55.62% 55.61% -0.01% =========================================== Files 620 620 Lines 96949 96965 +16 =========================================== + Hits 53929 53930 +1 - Misses 43020 43035 +15 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.