Skip to content

Quantization of BERT to deploy on a CIM accelerator

Notifications You must be signed in to change notification settings

anniezyao/cimbert

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Install and Setup

  1. Install uv and install Python 3.11
curl -LsSf https://astral.sh/uv/install.sh | sh
uv python install 3.11
  1. Clone the repository

git clone git@github.com:anniezyao/cimbert.git

  1. Enter the directory and initialize the project
cd cimbert
uv init
  1. Create and activate a virtual environment with Python 3.11
uv venv --python=3.11
source .venv/bin/activate
  1. Install dependencies
uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
uv pip install -r requirements.txt
  1. Copy transformers lib and replace ibert model
cp -r .venv/lib/python3.11/site-packages/transformers .
cp mod_transformers/* transformers/models/ibert/
  1. Run training.py
~/.venv/bin/python ~/training.py

About

Quantization of BERT to deploy on a CIM accelerator

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •