Xinyue Liu

icon indicating a website link https://cauchy221.github.io/

icon company Carnegie Mellon University icon location Pittsburgh, PA icon location MCDS @ CMU | RA @ CMU | DS (NLP) Intern @ Walmart | CS @ BUPT

Results 4 comments of Xinyue Liu

tokenizer.pad_token

Yes I think so. You can just set the `pad_token = eos_token` during training.

the current text generation call will exceed the model's predefined maximum length (4096)

Same question here. [Edit] Find an explanation to this question: #80

the current text generation call will exceed the model's predefined maximum length (4096)

> > Same question here. [Edit] Find an explanation to this question: #80 > > I reset the config, but it still had the warning"the current text generation call will...

[Bug]: Can't use yarn rope config for long context in Qwen2 model

> > What is your transformers and vLLM version? Can you show the stack trace of the error? > > I didn't try the server approach, and general vllm offline...