-
Notifications
You must be signed in to change notification settings - Fork 24
Issues: alibaba/ChatLearn
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
while self.generation_config.eos_token_id is list type, self.tokenizer.eos_token_id wiil be set to None
#263
opened Feb 27, 2025 by
haiasd
[train_rlhf_llama] When using vllm,Time-consuming optimization is not obvious as expectation.
#197
opened Dec 31, 2024 by
tkqie
[Alignment training (DPO)] Megatron support for QWEN2.5 series models
#183
opened Dec 18, 2024 by
Hevans123
[Feature]Use Megatron-core dist_checkpointing to load checkpoint with different parallel strategies
#169
opened Dec 5, 2024 by
SeaOfOcean
[Feature]support to parameter sync when trainer_tp divides inference_tp for megatron core model
#105
opened Sep 25, 2024 by
charles9304
ProTip!
Mix and match filters to narrow down what you’re looking for.