Research

65 updates on Research.

  1. RWKV trains like a transformer and runs with constant memory per token

    The paper releases pretrained RNN weights from 169M to 14B parameters and reports constant time and memory per token during inference.

  2. LaMini-LM distils models from 61M parameters up on 2.58M instructions

    MBZUAI distilled 17 instruction models from 61M to 7B parameters on 2.58M synthetic instructions, and reports the 248M model matching LLaMA-7B.

  3. MobileBERT runs in 62 ms on a Pixel 4 with 25.3M parameters

    Carnegie Mellon and Google Brain distilled BERT into a 25.3M-parameter model that answers in 62 ms on a Pixel 4 and scores 77.7 on GLUE.

  4. Hugging Face's DistilBERT is 40% smaller than BERT and 71% faster on an iPhone

    The 66M-parameter distilled BERT keeps 97% of its teacher on GLUE and weighs 207 MB inside a question-answering app on an iPhone 7 Plus.

  5. TinyBERT shrinks BERT-base to 14.5M parameters and runs 9.4x faster

    Huawei's distilled BERT keeps more than 96.8% of its teacher's GLUE score at 14.5M parameters, 7.5x smaller and 9.4x faster on inference.