-
Notifications
You must be signed in to change notification settings - Fork 395
Pull requests: InternLM/xtuner
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Patch] Skip calculate loss of empty
<think></think> (ಥ﹏ಥ)
#1387
opened Dec 24, 2025 by
HAOCHENYE
Loading…
[Fix] add printing token-level entropy and fix get_model_config_from_hf in example config
#1384
opened Dec 23, 2025 by
YanhuiDua
Loading…
[Fix] Fix device mismatch for ascend npu when loss_cfg.loss_reduction != "token"
#1365
opened Dec 15, 2025 by
nil0x9
Loading…
[Fix] Fix Division-by-zero error when warmup steps set the same as total steps
#1285
opened Nov 21, 2025 by
nil0x9
Loading…
[Fix] Add quantization config when saving fp8 and save tokenizer in offline dcp2hf
#1282
opened Nov 21, 2025 by
HAOCHENYE
Loading…
[Feature] Support group router based balance loss in
BalancingLoss
#1267
opened Nov 17, 2025 by
HAOCHENYE
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.