ccx1324andccx 5a942527b2 fix: inject LoRA before loading checkpoint state_dict ...

move inject_lora() before load_state_dict in _before_wrap so that
  LoRA adapter weights from a checkpoint are properly restored on
  training resume. Previously, inject happened after load, causing
  lora_A/lora_B keys to be silently ignored (strict=False).

  Co-Authored-By: ccx1324 <2424441089@qq.com>

2026-07-20 17:00:24 +08:00

..

config

feat: add online rollout framework for RL strategies

2026-07-20 03:49:56 +08:00

dataset

refactor: move sample-id indexing from dataset to store

2026-07-19 16:02:50 +08:00

extension

refactor: stride-based attn interface with layout and causal mask

2026-07-14 21:34:42 +08:00

inference

refactor: map instruction/input/output to chat roles

2026-07-20 13:55:25 +08:00

model

fix: create LoRA parameters on base weight device instead of CPU

2026-07-20 16:11:48 +08:00

parallel

feat: add FSDP2Executor using torch.distributed.fsdp.fully_shard API

2026-07-20 01:46:25 +08:00

preprocessing

refactor: map instruction/input/output to chat roles

2026-07-20 13:55:25 +08:00

serialization

fix: memmap mode=r, tool parser json.loads, greedy decode

2026-07-19 16:38:28 +08:00

tokenize

fix: make tokenizer picklable for spawn multiprocessing

2026-07-19 11:59:55 +08:00

trainer

fix: inject LoRA before loading checkpoint state_dict

2026-07-20 17:00:24 +08:00

__init__.py

chore: bump to 1.3.10

2026-07-19 16:40:27 +08:00

factory.py

fix: ForwardRef._evaluate Python 3.12 compatibility

2026-07-03 18:41:19 +08:00

protocols.py

refactor: 重构训练后端为 Executor 模式

2026-05-24 20:35:44 +08:00