Two-stage neural architecture search for large language models
Project description
whittle
A framework for two-stage neural architecture search (NAS) and structural pruning on language models.
Setup
- clone this repository:
git clone git@github.com:whittle-org/whittle.git cdinto the repository:cd whittle- Create a new conda environment and activate:
conda create -n whittle python=3.11 -y && conda activate whittle - Install the dependencies:
pip install .
Note: the library supports and is tested for python 3.9 to 3.11
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
whittle-0.1.3.tar.gz
(58.8 kB
view details)
Built Distribution
whittle-0.1.3-py3-none-any.whl
(58.5 kB
view details)
File details
Details for the file whittle-0.1.3.tar.gz.
File metadata
- Download URL: whittle-0.1.3.tar.gz
- Upload date:
- Size: 58.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d5b88adcfa34ade8ab795f4829b3faebc59524096daf279ecc73bc1de1089aaa |
|
| MD5 | d3b770465bb8734afb108bb13542e87e |
|
| BLAKE2b-256 | 0eb515c1b03d09c02ba7ca4092d33ef8bd4b236b4fddede593b7187ecaff1a73 |
File details
Details for the file whittle-0.1.3-py3-none-any.whl.
File metadata
- Download URL: whittle-0.1.3-py3-none-any.whl
- Upload date:
- Size: 58.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d7268ded2ab38abd0ef3a52ecb0f93773080006d9213f67c995a7cad43827a7e |
|
| MD5 | 841dae6e83f18c4c0c072417c60b4140 |
|
| BLAKE2b-256 | e9dfdb9535e16f040c3c64e223d9e77842c67e2ade40e9c0eebb62e24065f0e6 |
