m2-bert-110M / README.md
danfu09's picture
Update README.md
e684881
|
raw
history blame
374 Bytes
metadata
license: apache-2.0
language:
  - en
pipeline_tag: text-classification

Monarch Mixer-BERT

The 110M checkpoint for M2-BERT-base from the paper Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture.

Check out our GitHub for instructions on how to download and fine-tune it!