Token Efficient Fine Tuning (TEFT)
A library reducing the output size of large language models (LLM)
Build
Put pypi credentials in ~/.pypirc. The relevant section should look like this
[distutils]
index-servers =
testpypi
[pypi]
username = __token__
password = pypi-...
[testpypi]
username = __token__
password = pypi-...
python -m build
Upload to test index:
twine upload --repository testpypi dist/*
Upload to prod index:
twine upload dist/*
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
teft-0.0.1.tar.gz
(1.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
teft-0.0.1-py3-none-any.whl
(1.4 kB
view details)
File details
Details for the file teft-0.0.1.tar.gz.
File metadata
- Download URL: teft-0.0.1.tar.gz
- Upload date:
- Size: 1.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/4.0.2 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cafa2d66b828c63cd68db2068f0c958898dcff1eb3e079637c3526405efa582a
|
|
| MD5 |
5af42dcb406e06b78b5d2ab2f59c804f
|
|
| BLAKE2b-256 |
fd24b66217ef7df850c50c745a490546553d5c8728ef0f8f3171d933bf603243
|
File details
Details for the file teft-0.0.1-py3-none-any.whl.
File metadata
- Download URL: teft-0.0.1-py3-none-any.whl
- Upload date:
- Size: 1.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/4.0.2 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7a2a8950a7a550cd23334024c13125f3b7b1b792f78f0dd318c2552c0be6d4fa
|
|
| MD5 |
b44f952bf7f018d43e07ddc735727b80
|
|
| BLAKE2b-256 |
980dffdc1f0f6a4ef9a7360e8cedeafbc05927b7f99ac7574183b118bca3aa40
|
