Skip to content
@whyNLP

whyNLP

NLP research projects for Haoyi Wu.

Popular repositories Loading

  1. LCKV 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 147 10

  2. Conic10K Conic10K Public

    Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.

    Python 25 2

  3. Probabilistic-Transformer Probabilistic-Transformer Public

    A probabilitic model for contextual word representation. Accepted to ACL2023 Findings.

    Python 23 2

  4. tinyllama tinyllama Public

    A side project that follows all the acceleration tricks in tinyllama, with the minimal modification to the huggingface transformers code.

    Python 13 1

  5. nni-slurm nni-slurm Public

    Forked from microsoft/nni

    A patch for NNI with slurm and W&B.

    Python 8

  6. tinyllama-zh tinyllama-zh Public

    A side project that pretrains a tinyllama on Chinese corpora, with the minimal modification to the huggingface transformers code.

    Python 7 1

Repositories

Showing 7 of 7 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.

    whyNLP/LCKV’s past year of commit activity
    Python 147 10 1 1 Updated Jan 23, 2025
  • hf-starter Public template

    General starter code for creative model architecture with huggingface transformer library.

    whyNLP/hf-starter’s past year of commit activity
    Python 1 0 0 0 Updated Jan 16, 2025
  • tinyllama Public

    A side project that follows all the acceleration tricks in tinyllama, with the minimal modification to the huggingface transformers code.

    whyNLP/tinyllama’s past year of commit activity
    Python 13 1 1 0 Updated Sep 2, 2024
  • tinyllama-zh Public

    A side project that pretrains a tinyllama on Chinese corpora, with the minimal modification to the huggingface transformers code.

    whyNLP/tinyllama-zh’s past year of commit activity
    Python 7 MIT 1 0 0 Updated Mar 11, 2024
  • Conic10K Public

    Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.

    whyNLP/Conic10K’s past year of commit activity
    Python 25 MIT 2 0 0 Updated Dec 6, 2023
  • Probabilistic-Transformer Public

    A probabilitic model for contextual word representation. Accepted to ACL2023 Findings.

    whyNLP/Probabilistic-Transformer’s past year of commit activity
    Python 23 MIT 2 0 0 Updated Oct 22, 2023
  • nni-slurm Public Forked from microsoft/nni

    A patch for NNI with slurm and W&B.

    whyNLP/nni-slurm’s past year of commit activity
    Python 8 MIT 1,859 1 0 Updated Apr 16, 2023

Top languages

Loading…

Most used topics

Loading…