trl-mcsd / tests /experimental

293 kB

Ctrl+K

1 contributor

History: 1 commit

ihbkaiser

Implement MCSD for experimental SDPO

1fa3c6c verified 4 months ago

__init__.py
624 Bytes
Implement MCSD for experimental SDPO 4 months ago
test_async_grpo_trainer.py
5.93 kB
Implement MCSD for experimental SDPO 4 months ago
test_bco_trainer.py
17.6 kB
Implement MCSD for experimental SDPO 4 months ago
test_cpo_trainer.py
7.65 kB
Implement MCSD for experimental SDPO 4 months ago
test_dppo_trainer.py
7.75 kB
Implement MCSD for experimental SDPO 4 months ago
test_gkd_trainer.py
12.8 kB
Implement MCSD for experimental SDPO 4 months ago
test_gold_trainer.py
37.9 kB
Implement MCSD for experimental SDPO 4 months ago
test_grpo_with_replay_buffer_trainer.py
12.7 kB
Implement MCSD for experimental SDPO 4 months ago
test_gspo_token_trainer.py
2.48 kB
Implement MCSD for experimental SDPO 4 months ago
test_kto_trainer.py
12.9 kB
Implement MCSD for experimental SDPO 4 months ago
test_merge_model_callback.py
3.25 kB
Implement MCSD for experimental SDPO 4 months ago
test_minillm_trainer.py
2.31 kB
Implement MCSD for experimental SDPO 4 months ago
test_modeling_value_head.py
4.45 kB
Implement MCSD for experimental SDPO 4 months ago
test_nash_md_trainer.py
8.25 kB
Implement MCSD for experimental SDPO 4 months ago
test_online_dpo_trainer.py
17.8 kB
Implement MCSD for experimental SDPO 4 months ago
test_orpo_trainer.py
6.35 kB
Implement MCSD for experimental SDPO 4 months ago
test_ppo_trainer.py
37.5 kB
Implement MCSD for experimental SDPO 4 months ago
test_prm_trainer.py
16.2 kB
Implement MCSD for experimental SDPO 4 months ago
test_sdft_trainer.py
12.2 kB
Implement MCSD for experimental SDPO 4 months ago
test_sdpo_trainer.py
32.6 kB
Implement MCSD for experimental SDPO 4 months ago
test_ssd_trainer.py
7.2 kB
Implement MCSD for experimental SDPO 4 months ago
test_tpo_trainer.py
14.1 kB
Implement MCSD for experimental SDPO 4 months ago
test_utils.py
6.88 kB
Implement MCSD for experimental SDPO 4 months ago
test_xpo_trainer.py
5.54 kB
Implement MCSD for experimental SDPO 4 months ago