princeton-nlp / LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
https://arxiv.org/abs/2310.06694
MIT License
563 stars 47 forks source link

save model meet problem #56

Open 18140663659 opened 9 months ago

18140663659 commented 9 months ago

when i use the prune.sh and save model, i meet this problem:

image
xiamengzhou commented 9 months ago

Hi, it mostly seems like a out of memory issue. Could you make sure that your cpu memory is sufficient for saving model weights?