Wing Lian 66c3e5a3fd better handling of dora merge on Conv layers in Qwen 3.5 (#3599) ...

* better handling of dora merge on Conv layers in Qwen 3.5

* address issues from code review

* stricter efficient merges for dora since we now have meta model to reference

2026-04-12 10:57:45 -04:00

..

callbacks

feat: save checkpoint after training started (#3233)

2025-11-13 10:21:05 -05:00

data

fix: DPO tool role KeyError (#3217), dataset hash output_dir (#3303), config validators (#3538) [skip ci]

2026-04-01 19:57:07 -04:00

lora

better handling of dora merge on Conv layers in Qwen 3.5 (#3599)

2026-04-12 10:57:45 -04:00

schemas/validation

fix: DPO tool role KeyError (#3217), dataset hash output_dir (#3303), config validators (#3538) [skip ci]

2026-04-01 19:57:07 -04:00

test_grpo_rw_fnc.py

feat:openenv rollout_func (#3239) [skip ci]

2025-11-07 08:51:40 -05:00

test_import_helper.py

allow custom trainer_cls to be defined as a module reference in the YAML (#3024) [skip ci]

2025-08-06 22:49:19 -04:00

test_mistral3_processor.py

fix: update MistralProcessor to be v5 compat (#3423)

2026-02-23 11:39:13 -05:00

test_train.py

[GPT-OSS] improve FSDP shard merging and documentation for GPT-OSS (#3073)

2025-08-15 21:25:01 -04:00