butterluo

请问这个代码在测试集上的准确率和召回率分别是多少呢

8

如题，谢谢！

did lightseq compare with marian ?

1

Did ls compare with marian(https://github.com/marian-nmt/marian) ? What is the result?

is there any example for multi-gpu training ?

1

is there any example for multi-gpu training (with fairseq and huggingface)?

Export the weights in normal pytorch stat_dict

8

Can lightseq export the weights in normal pytorch stat_dict after training using lightseq? It can be used for hugging face transformers or other pytorch lib to load and later use.

[fix] some param will be set to optimizer twice when using MLM transformer heads

11

summary: When using MMFTransformer with MLM head, an warning will occur which will be an error in future: "UserWarning: optimizer contains a parameter group with duplicate parameters; in future, this...

### Question When the code and dataset of LLaVA1.6 will be released?

Is there any plan to release the ScreenAgent weights' huggingface version? I found that the sat is hard to use, lack of ecosystem and only support few quantization method.

Could you release the script which can transform CogAgent weights' sat version to huggingface version?

1

### Feature request / 功能建议 The script which can transform CogAgent weights' sat version to huggingface version. ### Motivation / 动机 Many company use the huggingace transformers library, and sat...

Support GraphRAG

6

### Feature Request Could you support microsoft's GraphRAG ### Motivation The current RAG still has numerous deficiencies. Microsoft's Graph RAG could substantially improve RAG capabilities, and I hope it will...

When the distributed GRPO training will be supported?

1

When the distributed GRPO training will be supported?