Skip to content

@whyNLP whyNLP

Change the repository type filter

All

    Repositories list

    6 repositories

    • LCKV

      Public
      Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.
      Python
      •8•146•2•1•Updated Dec 8, 2024Dec 8, 2024

    • tinyllama

      Public
      A side project that follows all the acceleration tricks in tinyllama, with the minimal modification to the huggingface transformers code.
      Python
      •0•13•1•0•Updated Sep 2, 2024Sep 2, 2024

    • tinyllama-zh

      Public
      A side project that pretrains a tinyllama on Chinese corpora, with the minimal modification to the huggingface transformers code.
      Python
      •
      MIT License
      •1•7•0•0•Updated Mar 11, 2024Mar 11, 2024

    • Conic10K

      Public
      Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.
      Python
      •
      MIT License
      •2•25•0•0•Updated Dec 6, 2023Dec 6, 2023

    • Probabilistic-Transformer

      Public
      A probabilitic model for contextual word representation. Accepted to ACL2023 Findings.
      Python
      •
      MIT License
      •2•21•0•0•Updated Oct 22, 2023Oct 22, 2023

    • nni-slurm

      Public
      A patch for NNI with slurm and W&B.
      Python
      •
      MIT License
      •1.8k•8•1•0•Updated Apr 16, 2023Apr 16, 2023