A framework for training and evaluating neural IR models.
Project description
Rankers
A small extension to transformers adding common IR loss components, easy wrappers and callbacks!
Install
pip install rankers
Latest (Unstable)
pip install -U git+https://github.com/Parry-Parry/rankers.git
Getting Started
Models can be instantiated like huggingface models, for example a bi-encoder (dot)
model = Dot.from_pretrained("bert-base-uncased")
Models are converted into rankers in PyTerrier:
ranker = model.to_pyterrier()
The core of Rankers is the RankerTrainer class, which inherits functionality from the Transformers trainer.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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
File details
Details for the file rankers-0.0.3.tar.gz.
File metadata
- Download URL: rankers-0.0.3.tar.gz
- Upload date:
- Size: 22.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
24a56d37f7292551ef257aaf8fb7448f3538aa5744eaab03c37c837296c2ede7
|
|
| MD5 |
1c35d2ae0a76d162dc95017bc07290e6
|
|
| BLAKE2b-256 |
d64d81a25270798d6126718dec567c0eec974faad43c994a44f4c8cf66c94e93
|
File details
Details for the file rankers-0.0.3-py3-none-any.whl.
File metadata
- Download URL: rankers-0.0.3-py3-none-any.whl
- Upload date:
- Size: 28.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3f3a95d8c39338007a119e80dbd0ae9ee92376993c1b25f349eea039ba37c0cd
|
|
| MD5 |
56d740ef91df459beccb778cc04c84a5
|
|
| BLAKE2b-256 |
7a22ffea538b43acea46f412bcb170ba9fd7456c7811be546682742df448e46a
|
